These are the SPP publications
2017
- J. A. Shelton, J. Gasthaus, Z. Dai, J. Lücke, and A. Gretton: Gp-select: accelerating em using adaptive subspace preselection. Neural computation, 29, 2177-2202, MIT Press, 2017. [Bibtex]
@Article{ SheltonEtAl2017, title = {GP-select: Accelerating EM using adaptive subspace preselection}, author = {Shelton, Jacquelyn A and Gasthaus, Jan and Dai, Zhenwen and L{\"u}cke, J{\"o}rg and Gretton, Arthur}, journal = {Neural Computation}, year = {2017}, pages = {2177--2202}, volume = {29}, number = {8}, publisher = {MIT Press}, url = {http://www.mitpressjournals.org/doi/abs/10.1162/NECO_a_00982} } - R. Holca-Lamarre, J. Lücke, and K. Obermayer: Models of acetylcholine and dopamine signals differentially improve neural representations. Frontiers in computational neuroscience, 11, 54, Frontiers, 2017. [Bibtex]
@Article{ HolcaEtAl2017, title = {Models of Acetylcholine and Dopamine Signals Differentially Improve Neural Representations}, author = {Holca-Lamarre, Rapha{\"e}l and L{\"u}cke, J{\"o}rg and Obermayer, Klaus}, journal = {Frontiers in Computational Neuroscience}, year = {2017}, volume = {11}, pages = {54}, publisher = {Frontiers}, doi = {10.3389/fncom.2017.00054}, url = {http://journal.frontiersin.org/article/10.3389/fncom.2017.00054/full} } - D. Forster and J. Lücke: Truncated variational EM for semi-supervised Neural Simpletrons. In International joint conference on neural networks (ijcnn), 3769-3776, 2017. [Bibtex]
@InProceedings{ ForsterLucke2017, author = {Forster, Dennis and L{\"u}cke, J{\"o}rg}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, title = {Truncated Variational {EM} for Semi-Supervised {N}eural {S}impletrons}, year = {2017}, pages = {3769-3776}, url = {http://ieeexplore.ieee.org/document/7966331/} } - S. Drgas, T. Virtanen, J. Lücke, and A. Hurmalainen: Binary non-negative matrix deconvolution for audio dictionary learning. Ieee/acm transactions on audio, speech, and language processing, 25, 1644-1656, IEEE, 2017. [Bibtex]
@Article{ DrgasEtAl2017, title = {Binary non-negative matrix deconvolution for audio dictionary learning}, author = {Drgas, Szymon and Virtanen, Tuomas and L{\"u}cke, J{\"o}rg and Hurmalainen, Antti}, journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing}, year = {2017}, pages = {1644-1656}, volume = {25}, publisher = {IEEE}, url = {http://ieeexplore.ieee.org/document/7935444/} }
2016
- A. -S. Sheikh and J. Lücke: Select-and-sample for spike-and-slab sparse coding. In Advances in neural information processing systems (nips), 29, 3927-3935, 2016. [Bibtex]
@InProceedings{ SheikhLucke2016, title = {Select-and-Sample for Spike-and-Slab Sparse Coding}, author = {A.-S. Sheikh and J. L{\"u}cke}, booktitle = {Advances in Neural Information Processing Systems (NIPS)}, pages = {3927--3935}, volume = {29}, year = {2016}, url = {http://papers.nips.cc/paper/6276-select-and-sample-for-spike-and-slab-sparse-coding} } - B. Paassen, B. Mokbel, and B. Hammer: Adaptive structure metrics for automated feedback provision in intelligent tutoring systems. Neurocomputing, 192, Elsevier Science Publishers B. V., 2016. [Bibtex]
@Article{ Paassen2016Neurocomputing, abstract = {Typical intelligent tutoring systems rely on detailed domain-knowledge which is hard to obtain and difficult to encode. As a data-driven alternative to explicit domain-knowledge, one can present learners with feedback based on similar existing solutions from a set of stored examples. At the heart of such a data-driven approach is the notion of similarity. We present a general-purpose framework to construct structure metrics on sequential data and to adapt those metrics using machine learning techniques. We demonstrate that metric adaptation improves the classification of wrong versus correct learner attempts in a simulated data set from sports training, and the classification of the underlying learner strategy in a real Java programming dataset.}, author = {Paassen, Benjamin and Mokbel, Bassam and Hammer, Barbara}, journal = {Neurocomputing}, keyword = {metric learning, intelligent tutoring systems, sequential data, learning vector quantization, algebraic dynamic programming}, publisher = {Elsevier Science Publishers B. V.}, title = {{Adaptive structure metrics for automated feedback provision in intelligent tutoring systems}}, doi = {doi:10.1016/j.neucom.2015.12.108}, volume = {192}, year = {2016}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/paassen_mokbel_hammer_neurocomputing_2015_preprint.pdf} } - B. Paassen, C. Göpfert, and B. Hammer: Gaussian process prediction for time series of structured data. In Proceedings of the esann, 24th european symposium on artificial neural networks, computational intelligence and machine learning, 2016. [Bibtex]
@InProceedings{ Paassen2016ESANN, abstract = {Time series prediction constitutes a classic topic in machine learning with wide-ranging applications, but mostly restricted to the domain of vectorial sequence entries. In recent years, time series of structured data (such as sequences, trees or graph structures) have become more and more important, for example in social network analysis or intelligent tutoring systems. In this contribution, we propose an extension of time series models to strucured data based on Gaussian processes and structure kernels. We also provide speedup techniques for predictions in linear time, and we evaluate our approach on real data from the domain of intelligent tutoring systems.}, author = {Paassen, Benjamin and G{\"o}pfert, Christina and Hammer, Barbara}, booktitle = {Proceedings of the ESANN, 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning}, editor = {Verleysen, Michele}, keyword = {structured data, gaussian processes, time series prediction}, location = {Bruges}, title = {{Gaussian process prediction for time series of structured data}}, year = {2016}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/paassen_goepfert_hammer_2016_gaussian_process_prediction_preprint.pdf} } - Monk T., Savin C., and J. Lücke: Neurons equipped with intrinsic plasticity learn stimulus intensity statistics. In Advances in neural information processing systems, 29, 4278-4286, 2016. [Bibtex]
@InProceedings{ MonkEtAl2016, author = {Monk, T., and Savin, C., and L{\"u}cke, J.}, title = {Neurons Equipped with Intrinsic Plasticity Learn Stimulus Intensity Statistics}, booktitle = {Advances in Neural Information Processing Systems}, pages = {4278-4286}, volume = {29}, year = {2016}, url = {http://papers.nips.cc/paper/6582-neurons-equipped-with-intrinsic-plasticity-learn-stimulus-intensity-statistics} } - R. Martín-Martín, S. Höfer, and O. Brock: An Integrated Approach to Visual Perception of Articulated Objects. In Proceedings of the 2016 IEEE International Conference on Robotics and Automotion (ICRA), in press, IEEE, 2016. [Bibtex]
@InProceedings{ martin-martin_integrated_2016, address = {Stockholm, Sweden}, title = {An {Integrated} {Approach} to {Visual} {Perception} of {Articulated} {Objects}}, booktitle = {Proceedings of the 2016 {IEEE} {International} {Conference} on {Robotics} and {Automotion} ({ICRA})}, publisher = {IEEE}, author = {Martín-Martín, Roberto and Höfer, Sebastian and Brock, Oliver}, year = {2016}, pages = {in press}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/martin_hoefer_15_iros_sr_opt.pdf} } - R. Akrour, A. Abdolmaleki, H. Abdulsamad, and G. Neumann: Model-free trajectory optimization for reinforcement learning. In Proceedings of the 33rd international conference on machine learning, ICML 2016, new york, ny, usa, 19-24 june 2016, 2016. [Bibtex]
@InProceedings{ AkrourAAN16, title = {Model-free Trajectory Optimization for Reinforcement Learning}, author = {Riad Akrour and Abbas Abdolmaleki and Hany Abdulsamad and Gerhard Neumann}, booktitle = {Proceedings of the 33rd International Conference on Machine Learning, {ICML} 2016, New York, NY, USA, 19-24 June 2016}, year = {2016}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/full_moto_16.pdf} }
2015
- M. Wistuba, N. Schilling, and L. Schmidt-Thieme: Hyperparameter search space pruning – a new component for sequential model-based hyperparameter optimization. In Proceedings of european conference on machine learning and principles and practice of knowledge discovery in databases (ecml’15), Springer, 2015. [Bibtex]
@InProceedings{ wistuba2015, title = {Hyperparameter Search Space Pruning - A New Component for Sequential Model-Based Hyperparameter Optimization}, author = {Wistuba, Martin and Schilling, Nicolas and Schmidt-Thieme, Lars}, booktitle = {Proceedings of European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML'15)}, year = {2015}, publisher = {Springer}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/wistuba-ecml-2015.pdf} } - O. Walter, R. Häb-Umbach, B. Mokbel, B. Paaßen, and B. Hammer: Autonomous learning of representations. Ki – künstliche intelligenz, 1-13, Springer Berlin Heidelberg, 2015. [Bibtex]
@Article{ walter2015ki, abstract = {Besides the core learning algorithm itself, one major question in machine learning is how to best encode given training data such that the learning technology can efficiently learn based thereon and generalize to novel data. While classical approaches often rely on a hand coded data representation, the topic of autonomous representation or feature learning plays a major role in modern learning architectures. The goal of this contribution is to give an overview about different principles of autonomous feature learning, and to exemplify two principles based on two recent examples: autonomous metric learning for sequences, and autonomous learning of a deep representation for spoken language, respectively.}, author = {Walter, Oliver and H{\"a}b-Umbach, Reinhold and Mokbel, Bassam and Paa{\ss}en, Benjamin and Hammer, Barbara}, issn = {0933-1875}, journal = {KI - K{\"u}nstliche Intelligenz}, language = {English}, pages = {1--13}, publisher = {Springer Berlin Heidelberg}, title = {Autonomous Learning of Representations}, url = {http://link.springer.com/article/10.1007/s13218-015-0372-1}, doi = {10.1007/s13218-015-0372-1}, year = {2015}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/Learning_Representations.pdf} } - O. Walter, R. Haeb-Umbach, J. Strunk, and N. P. Himmelmann: Lexicon discovery for language preservation using unsupervised word segmentation with pitman-yor language models. 2015. [Bibtex]
@TechReport{ WaHaStHi15, title = {Lexicon Discovery for Language Preservation using Unsupervised Word Segmentation with Pitman-Yor Language Models}, author = {Walter, Oliver and Haeb-Umbach, Reinhold and Strunk, Jan and P. Himmelmann, Nikolaus }, institution = {University of Paderborn Department of Communications Engineering}, year = {2015}, number = {FGNT-2015-01}, type = {FGNT Technical Report}, abstract = {In this paper we show that recently developed algorithms for unsupervised word segmentation can be a valuable tool for the documentation of endangered languages. We applied an unsupervised word segmentation algorithm based on a nested Pitman-Yor language model to two austronesian languages, Wooi and Waima'a. The algorithm was then modified and parameterized to cater the needs of linguists for high precision of lexical discovery: We obtained a lexicon precision of of 69.2\% and 67.5\% for Wooi and Waima'a, respectively, if single-letter words and words found less than three times were discarded. A comparison with an English word segmentation task showed comparable performance, verifying that the assumptions underlying the Pitman-Yor language model, the universality of Zipf's law and the power of n-gram structures, do also hold for languages as exotic as Wooi and Waima'a.}, url = {http://nt.uni-paderborn.de/public/pubs/2015/WaHaStHi.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/WaHaStHi.pdf} } - O. Walter, L. Drude, and R. Haeb-Umbach: Source counting in speech mixtures by nonparametric bayesian estimation of an infinite gaussian mixture model. In 40th international conference on acoustics, speech and signal processing (icassp 2015), 2015. [Bibtex]
@InProceedings{ WaDrHa2015, title = {Source Counting in Speech Mixtures by Nonparametric Bayesian Estimation of an infinite Gaussian Mixture Model}, author = {Walter, Oliver and Drude, Lukas and Haeb-Umbach, Reinhold}, booktitle = {40th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015)}, year = {2015}, month = {april}, abstract = {In this paper we present a source counting algorithm to determine the number of speakers in a speech mixture. In our proposed method, we model the histogram of estimated directions of arrival with a nonparametric Bayesian infinite Gaussian mixture model. As an alternative to classical model selection criteria and to avoid specifying the maximum number of mixture components in advance, a Dirichlet process prior is employed over the mixture components. This allows to automatically determine the optimal number of mixture components that most probably model the observations. We demonstrate by experiments that this model outperforms a parametric approach using a finite Gaussian mixture model with a Dirichlet distribution prior over the mixture weights.}, comment = {<a href="http://nt.uni-paderborn.de/public/pubs/2015/WaDrHa15_Poster.pdf">[Poster]</a>}, url = {http://nt.uni-paderborn.de/public/pubs/2015/WaDrHa15.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/WaDrHa15.pdf} } - M. Toussaint, H. Ritter, and O. Brock: The optimization route to robotics and alternatives. Ki – künstliche intelligenz, 29, 379-388, Springer Berlin Heidelberg, 2015. [Bibtex]
@Article{ Toussaint2015Ki, year = {2015}, issn = {0933-1875}, journal = {KI - Künstliche Intelligenz}, volume = {29}, number = {4}, doi = {10.1007/s13218-015-0379-7}, title = {The Optimization Route to Robotics and Alternatives}, url = {http://link.springer.com/article/10.1007/s13218-015-0379-7}, publisher = {Springer Berlin Heidelberg}, author = {Toussaint, Marc and Ritter, Helge and Brock, Oliver}, pages = {379-388}, language = {English}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/15-toussaint-KI.pdf} } - N. Schilling, M. Wistuba, L. Drumond, and L. Schmidt-Thieme: Hyperparameter optimization with factorized multilayer perceptrons. In Proceedings of european conference on machine learning and principles and practice of knowledge discovery in databases (ecml’15), Springer, 2015. [Bibtex]
@InProceedings{ schilling2015, title = {Hyperparameter Optimization with Factorized Multilayer Perceptrons}, author = {Schilling, Nicolas and Wistuba, Martin and Drumond, Lucas and Schmidt-Thieme, Lars}, booktitle = {Proceedings of European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML'15)}, year = {2015}, publisher = {Springer}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/schilling-ecml-2015.pdf} } - Q. Li, R. Haschke, and H. Ritter: Visuo-tactile servoing for exploration and manipulation. In Iros2015 ws:see and touch: 1st workshop on multimodal sensor-based robot control for hri and soft manipulation, IEEE, 2015. [Bibtex]
@Conference{ QiangIROS2015WS, title = {Visuo-Tactile Servoing for Exploration and Manipulation}, booktitle = {IROS2015 WS:See and Touch: 1st Workshop on multimodal sensor-based robot control for HRI and soft manipulation}, year = {2015}, month = {28/09/2015}, publisher = {IEEE}, organization = {IEEE}, address = {Hamburg, Germany}, author = {Qiang Li and Robert Haschke and Helge Ritter}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/iros15ws.pdf} } - Q. Li, R. Haschke, and H. Ritter: A visuo-tactile control framework for manipulation and exploration of unknown objects. In Ieee ras humanoids conference, IEEE, 2015. [Bibtex]
@Conference{ QiangHumanoids2015vistac, title = {A Visuo-Tactile Control Framework for Manipulation and Exploration of Unknown Objects}, booktitle = {IEEE RAS Humanoids Conference}, year = {2015}, month = {3/11/2015}, publisher = {IEEE}, organization = {IEEE}, address = {Seoul, Korea}, author = {Qiang Li and Robert Haschke and Helge Ritter}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/visuotactileservo.pdf} } - Q. Li, R. Haschke, and H. Ritter: Towards body schema learning using training data acquired by continuous self-touch. In Ieee ras humanoids conference, IEEE, 2015. [Bibtex]
@Conference{ QiangHumanoids2015Calib, title = {Towards Body Schema Learning using Training Data Acquired by Continuous Self-touch}, booktitle = {IEEE RAS Humanoids Conference}, year = {2015}, month = {3/11/2015}, publisher = {IEEE}, organization = {IEEE}, address = {Seoul, Korea}, author = {Qiang Li and Robert Haschke and Helge Ritter}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/calib.pdf} } - S. Parisi, H. Abdulsamad, A. Paraschos, C. Daniel, and J. Peters: Reinforcement learning vs human programming in tetherball robot games. Proceedings of the ieee/rsj conference on intelligent robots and systems (iros), 2015. [Bibtex]
@InProceedings{ parisi_iros_2015, author = "Parisi, S. and Abdulsamad, H. and Paraschos, A. and Daniel, C. and Peters, J.", year = "2015", title = "Reinforcement Learning vs Human Programming in Tetherball Robot Games", journal = "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)", key = "scarl", url = "http://www.ausy.tu-darmstadt.de/uploads/Team/SimoneParisi/parisi_iros_2015", crossref = "p10833", pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/parisi_iros_2015.pdf} } - B. Paaßen: Interview with werner von seelen. Ki – künstliche intelligenz, 29, 445-448, Springer Berlin Heidelberg, 2015. [Bibtex]
@Article{ Paassen2015InterviewVonSeelen, year = {2015}, issn = {0933-1875}, journal = {KI - Künstliche Intelligenz}, volume = {29}, number = {4}, doi = {10.1007/s13218-015-0368-x}, title = {Interview with Werner von Seelen}, url = {http://dx.doi.org/10.1007/s13218-015-0368-x}, publisher = {Springer Berlin Heidelberg}, author = {Paaßen, Benjamin}, pages = {445-448}, language = {English}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/interview_werner_von_seelen.pdf} } - B. Paaßen, B. Mokbel, and B. Hammer: Adaptive structure metrics for automated feedback provision in java programming. 307-312, 2015. [Bibtex]
@InProceedings{ paassen2015esann, abstract = {Today's learning supporting systems for programming mostly rely on pre-coded feedback provision, such that their applicability is restricted to modelled tasks. In this contribution, we investigate the suitability of machine learning techniques to automate this process by means of a presentationm of similar solution strategies from a set of stored examples. To this end we apply structure metric learning methods in local and global alignment which can be used to compare Java programs. We demonstrate that automatically adapted metrics better identify the underlying programming strategy as compared to their default counterparts in a benchmark example from programming.}, author = {Paa{\ss}en, Benjamin and Mokbel, Bassam and Hammer, Barbara}, editor = {Michel Verleysen}, language = {English}, location = {Bruges, Belgium}, pages = {307--312}, title = {Adaptive structure metrics for automated feedback provision in Java programming}, year = {2015}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/paassen_mokbel_hammer_adaptive_structure_metrics.pdf} } - P. Ochs, R. Ranftl, T. Brox, and T. Pock: Bilevel optimization with nonsmooth lower level problems. In International conference on scale space and variational methods in computer vision (ssvm), 2015. [Bibtex]
@InProceedings{ OB15a, author = {P. Ochs and R. Ranftl and T. Brox and T. Pock}, title = {Bilevel Optimization with Nonsmooth Lower Level Problems}, booktitle = {International Conference on Scale Space and Variational Methods in Computer Vision (SSVM)}, year = {2015}, url = {http://lmb.informatik.uni-freiburg.de/Publications/2015/OB15a}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/2015_ochs_ssvm-bilevel.pdf} } - B. Mokbel, B. Paassen, Frank-Michael Schleif, and B. Hammer: Metric learning for sequences in relational LVQ. Neurocomputing, (accepted/in press), Elsevier Science Publishers B. V., 2015. [Bibtex]
@Article{ Neurocomputing2015-MokPaaSchleiHam, author = {Bassam Mokbel and Benjamin Paassen and Frank-Michael Schleif and Barbara Hammer}, title = {Metric learning for sequences in relational {LVQ}}, journal = {Neurocomputing}, publisher = {Elsevier Science Publishers B. V.}, address = {Amsterdam, The Netherlands}, year = {2015}, volume = {(accepted/in press)}, pages = {}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/MokbelEtAl2015-Neurocomputing-MetricLearningSequencesLVQ.pdf} } - M. Missura and S. Behnke: Online learning of bipedal walking stabilization. Ki – künstliche intelligenz, 29, 401-405, Springer Berlin Heidelberg, 2015. [Bibtex]
@Article{ kimissura, author = {Marcell Missura and Sven Behnke}, title = {Online Learning of Bipedal Walking Stabilization}, publisher = {Springer Berlin Heidelberg}, journal = {KI - Künstliche Intelligenz}, volume = {29}, number = {4}, pages = {401--405}, year = {2015}, issn = {0933-1875}, url = {http://link.springer.com/article/10.1007/s13218-015-0387-7}, doi = {10.1007/s13218-015-0387-7}, language = {English}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/2015_ki_Missura.pdf} } - K. Kersting and S. Natarajan: Statistical relational artificial intelligence: from distributions through actions to optimization. Ki – künstliche intelligenz, 29, 363-368, Springer Berlin Heidelberg, 2015. [Bibtex]
@Article{ Kersting2015ki, year = {2015}, issn = {0933-1875}, journal = {KI - Künstliche Intelligenz}, volume = {29}, number = {4}, title = {Statistical Relational Artificial Intelligence: From Distributions through Actions to Optimization}, publisher = {Springer Berlin Heidelberg}, author = {Kersting,Kristian and Natarajan, Sriraam}, pages = {363-368}, url = {http://link.springer.com/article/10.1007/s13218-015-0386-8}, doi = {10.1007/s13218-015-0386-8}, language = {English}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/kersting2015ki-1.pdf} } - F. Hutter, J. Lücke, and L. Schmidt-Thieme: Beyond manual tuning of hyperparameters. Ki — künstliche intelligenz, in press, Springer, 2015. [Bibtex]
@Article{ HutterEtAl2015, title = {Beyond Manual Tuning of Hyperparameters}, author = {Hutter, Frank and L{\"u}cke, J{\"o}rg and Schmidt-Thieme, Lars}, journal = {KI -- K{\"u}nstliche Intelligenz}, pages = {in press}, year = {2015}, publisher = {Springer}, url = {http://link.springer.com/article/10.1007/s13218-015-0381-0} } - S. Gross and N. Pinkwart: Towards an integrative learning environment for java programming. In Ieee 15th international conference on advanced learning technologies (icalt), 2015, 24-28, IEEE Computer Society Press, 2015. [Bibtex]
@InProceedings{ HUB-CSES/GP15b, author = {Gross, S. and Pinkwart, N.}, booktitle = {IEEE 15th International Conference on Advanced Learning Technologies (ICALT), 2015}, title = {Towards an Integrative Learning Environment for Java Programming}, year = {2015}, pages = {24-28}, keywords = {Education;Java;Learning systems;Problem-solving;Programming environments;Programming profession;Java;adaptive tutoring;integrative;learning environment;programming}, doi = {10.1109/ICALT.2015.75}, month = {July}, publisher = {IEEE Computer Society Press}, editor = {Sampson, D. G. and Huang, R. and Hwang, G.-J. and Liu, T.-Z. and Chen, N.-S. and Kinshuk and Tsai, C.-C.}, address = {Los Alamitos, CA}, url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true&arnumber=7265253}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/ICALT_Paper_2015.pdf} } - S. Gross and N. Pinkwart: How do learners behave in help-seeking when given a choice?. In Artificial intelligence in education, 9112, 600-603, Springer International Publishing, 2015. [Bibtex]
@InProceedings{ HUB-CSES/GP15a, title = {How Do Learners Behave in Help-Seeking When Given a Choice?}, author = {Gross, S. and Pinkwart, N.}, booktitle = {Artificial Intelligence in Education}, publisher = {Springer International Publishing}, year = {2015}, editor = {Conati, Cristina and Heffernan, Neil and Mitrovic, Antonija and Verdejo, M. Felisa}, pages = {600-603}, series = {Lecture Notes in Computer Science}, volume = {9112}, doi = {10.1007/978-3-319-19773-9_71}, isbn = {978-3-319-19772-2}, keywords = {Intelligent tutoring system; Help-seeking; Feedback choice}, url = {http://link.springer.com/chapter/10.1007%2F978-3-319-19773-9_71}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/AIED_Poster_2015.pdf} } - S. Gross, B. Mokbel, B. Hammer, and N. Pinkwart: Learning feedback in intelligent tutoring systems. Ki – künstliche intelligenz, 1-6, Springer Berlin Heidelberg, 2015. [Bibtex]
@Article{ gross2015ki, abstract = {Intelligent Tutoring Systems (ITSs) are adaptive learning systems that aim to support learners by providing one-on-one individualized instruction. Typically, instructing learners in ITSs is build on formalized domain knowledge and, thus, the applicability is restricted to well-defined domains where knowledge about the domain being taught can be explicitly modeled. For ill-defined domains, human tutors still by far outperform the performance of ITSs, or the latter are not applicable at all. As part of the DFG priority programme {\textacutedbl}Autonomous Learning{\textacutedbl}, the FIT project has been conducted over a period of 3 years pursuing the goal to develop novel ITS methods, that are also applicable for ill-defined problems, based on implicit domain knowledge extracted from educational data sets. Here, machine learning techniques have been used to autonomously infer structures from given learning data (e.g., student solutions) and, based on these structures, to develop strategies for instructing learners.}, author = {Gross, Sebastian and Mokbel, Bassam and Hammer, Barbara and Pinkwart, Niels}, issn = {0933-1875}, journal = {KI - K{\"u}nstliche Intelligenz}, language = {English}, pages = {1--6}, publisher = {Springer Berlin Heidelberg}, title = {Learning Feedback in Intelligent Tutoring Systems}, url = {http://link.springer.com/article/10.1007/s13218-015-0367-y}, doi = {10.1007/s13218-015-0367-y}, year = {2015}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/KI_Journal_Article_2015_revised.pdf} } - M. Feurer, T. Springenberg, and F. Hutter: Initializing bayesian hyperparameter optimization via meta-learning. In Proceedings of the twenty-ninth aaai conference on artificial intelligence, 2015. [Bibtex]
@InProceedings{ Feurer2015, lauthor = {Matthias Feurer and Tobias Springenberg and Frank Hutter}, author = {M. Feurer and T. Springenberg and F. Hutter}, title = {Initializing Bayesian Hyperparameter Optimization via Meta-Learning}, booktitle = {Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence}, conference = {AAAI Conference}, year = {2015}, month = jan } - A. Eitel, J. T. Springenberg, Luciano Spinello, M. Riedmiller, and W. Burgard: Multimodal deep learning for robust rgb-d object recognition. In Ieee/rsj international conference on intelligent robots and systems (iros), 2015. [Bibtex]
@InProceedings{ eitel15iros, author = {Andreas Eitel and Jost Tobias Springenberg and Luciano Spinello and Martin Riedmiller and Wolfram Burgard}, title = {Multimodal Deep Learning for Robust RGB-D Object Recognition}, booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, year = 2015, address = {Hamburg, Germany}, url = {http://ais.informatik.uni-freiburg.de/publications/papers/eitel15iros.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/eitel15iros.pdf} } - V. Despotovic, O. Walter, and R. Haeb-Umbach: Semantic analysis of spoken input using markov logic networks. In Interspeech 2015, 2015. [Bibtex]
@InProceedings{ DeWaHa, title = {Semantic Analysis of Spoken Input using Markov Logic Networks}, author = {Despotovic, Vladimir and Walter, Oliver and Haeb-Umbach, Reinhold}, booktitle = {INTERSPEECH 2015}, year = {2015}, month = {oct}, abstract = {We present a semantic analysis technique for spoken input using Markov Logic Networks (MLNs). MLNs combine graphical models with first-order logic. They areparticularly suitable for providing inference in the presence of inconsistent and incomplete data, which are typical of an automatic speech recognizer's (ASR) output in the presence of degraded speech. The target application is a speech interface to a home automation system to be operated by people with speech impairments, where the ASR output is particularly noisy. In order to cater for dysarthric speech with non-canonical phoneme realizations, acoustic representations of the input speech are learned in an unsupervised fashion. While training data transcripts are not required for the acoustic model training, the MLN training requires supervision, however, at a rather loose and abstract level. Results on two databases, one of them for dysarthric speech, show that MLN-based semantic analysis clearly outperforms baseline approaches employing non-negative matrix factorization, multinomial naive Bayes models, or support vector machines.}, comment = {<a href="http://nt.uni-paderborn.de/public/pubs/2015/DeWaHa_Poster.pdf">[Poster]</a>}, url = {http://nt.uni-paderborn.de/public/pubs/2015/DeWaHa.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/DeWaHa.pdf} } - W. Boehmer and K. Obermayer: Regression with linear factored functions. machine learning and knowledge discovery in databases. Lecture notes in computer science, 9284, 119-134, 2015. [Bibtex]
@Article{ Boehmer15b, author = {Boehmer, Wendelin and Obermayer, Klaus}, title = {Regression with Linear Factored Functions. Machine Learning and Knowledge Discovery in Databases}, journal = {Lecture Notes in Computer Science}, volume = {9284}, pages = {119-134}, year = {2015}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/Boehmer15b-ecml.pdf} } - W. Böhmer, J. Springenberg, J. Boedecker, M. Riedmiller, and K. Obermayer: Autonomous learning of state representations for control: an emerging field aims to autonomously learn state representations for reinforcement learning agents from their real-world sensor observations. Ki – künstliche intelligenz, 352-362, Springer Berlin Heidelberg, 2015. [Bibtex]
@Article{ Boehmer15a, author = {Böhmer, Wendelin and Springenberg, JostTobias and Boedecker, Joschka and Riedmiller, Martin and Obermayer, Klaus}, title = {Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations}, doi = {10.1007/s13218-015-0356-1}, journal = {KI - Künstliche Intelligenz}, publisher = {Springer Berlin Heidelberg}, pages = {352--362}, issn = {0933-1875}, year = {2015}, keywords = {End-to-end reinforcement learning; Representation learning; Deep auto-encoder networks; Slow feature analysis; Autonomous robotics}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/Boehmer15a-ki.pdf} } - N. Ay: Geometric design principles for brains of embodied agents. Ki – künstliche intelligenz, 29, 389-399, Springer Berlin Heidelberg, 2015. [Bibtex]
@Article{ Ay2015ki, year = {2015}, issn = {0933-1875}, journal = {KI - Künstliche Intelligenz}, volume = {29}, number = {4}, title = {Geometric Design Principles for Brains of Embodied Agents}, publisher = {Springer Berlin Heidelberg}, author = {Ay, Nihat}, pages = {389-399}, url = {http://link.springer.com/article/10.1007/s13218-015-0382-z}, doi = {10.1007/s13218-015-0382-z}, language = {English}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/Ay.pdf} } - J. Kulick, S. Otte, and M. Toussaint: Robots solving serial means-means-end problems. RSS Workshop on Combining AI Reasoning and Cognitive Science, 2015. [Bibtex]
@Misc{ 15-kulick-RSSws, key = "RSSws", author = "J. Kulick and S. Otte and M. Toussaint", title = "Robots Solving Serial Means-Means-End Problems", howpublished = "RSS Workshop on Combining AI Reasoning and Cognitive Science", year = "2015", pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/15-kulick-RSSws.pdf} } - J. Kulick, S. Otte, and M. Toussaint: Active exploration of joint dependency structures. In Proc. of the ieee int. conf. on robotics \& automation (icra 2015), 2015. [Bibtex]
@InProceedings{ 15-kulick-ICRA, key = "ICRA", author = "Johannes Kulick and Stefan Otte and Marc Toussaint", title = "Active Exploration of Joint Dependency Structures", booktitle = icra # " (ICRA 2015)", year = "2015", pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/15-kulick-ICRA.pdf} } - J. Kulick, R. Lieck, and M. Toussaint: The Advantage of Cross-Entropy over Entropy in Iterative Information Gathering. 2015. [Bibtex]
@Misc{ 15-kulick-Cross-Entropy, key = "MaxCE", author = "Johannes Kulick and Robert Lieck and Marc Toussaint", year = "2015", title = "{{The Advantage of Cross-Entropy over Entropy in Iterative Information Gathering}}", pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/1409.7552v2.pdf} }
2014
- O. Walter, V. Despotovic, R. Haeb-Umbach, J. Gemmeke, B. Ons, and H. Van hamme: An evaluation of unsupervised acoustic model training for a dysarthric speech interface. In Interspeech 2014, 2014. [Bibtex]
@InProceedings{ WaDeHaebGeOnVa14, title = {An Evaluation of Unsupervised Acoustic Model Training for a Dysarthric Speech Interface}, author = {Walter, Oliver and Despotovic, Vladimir and Haeb-Umbach, Reinhold and Gemmeke, Jrt and Ons, Bart and Van hamme, Hugo}, booktitle = {INTERSPEECH 2014}, year = {2014}, abstract = {In this paper, we investigate unsupervised acoustic model training approaches for dysarthric-speech recognition. These models are first, frame-based Gaussian posteriorgrams, obtained from Vector Quantization (VQ), second, so-called Acoustic Unit Descriptors (AUDs), which are hidden Markov models of phone-like units, that are trained in an unsupervised fashion, and, third, posteriorgrams computed on the AUDs. Experiments were carried out on a database collected from a home automation task and containing nine speakers, of which seven are considered to utter dysarthric speech. All unsupervised modeling approaches delivered significantly better recognition rates than a speaker-independent phoneme recognition baseline, showing the suitability of unsupervised acoustic model training for dysarthric speech. While the AUD models led to the most compact representation of an utterance for the subsequent semantic inference stage, posteriorgram-based representations resulted in higher recognition rates, with the Gaussian posteriorgram achieving the highest slot filling F-score of 97.02%. Index Terms: unsupervised learning, acoustic unit descriptors, dysarthric speech, non-negative matrix factorization}, comment = {<a href="http://nt.uni-paderborn.de/public/pubs/2014/WaDeHaebGeOnVa14_Poster.pdf">[Poster]</a> <a href="http://nt.uni-paderborn.de/public/pubs/2014/WaDeHaebGeOnVa14_Spotlight.pdf">[Spotlight]</a>}, url = {http://nt.uni-paderborn.de/public/pubs/2014/WaDeHaebGeOnVa14.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/WaDeHaebGeOnVa14.pdf} } - Q. Li, R. Haschke, and H. Ritter: Object exploration by visuo-tactile servoing. http://www.icub.org/other/icdl-epirob-2014/submissions/li.pdf, In Icdl2014 ws:development of body representations in humans and robots, IEEE, 2014. [Bibtex]
@Conference{ QiangICDL2014WS, title = {Object exploration by visuo-tactile servoing}, booktitle = {ICDL2014 WS:Development of body representations in humans and robots}, howpublished = {http://www.icub.org/other/icdl-epirob-2014/submissions/li.pdf}, year = {2014}, month = {13/10/2014}, publisher = {IEEE}, organization = {IEEE}, address = {Genoa, Italy}, author = {Qiang Li and Robert Haschke and Helge Ritter}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/object-exploration-by-visuo-tactile-servoing.pdf} } - M. Mladenov, A. Globerson, and K. Kersting: Lifted message passing as reparametrization of graphical models. In In proceedings of the 30th conference on uncertainty in artificial intelligence (uai), 2014. [Bibtex]
@InProceedings{ MlGlKeUAI14, author = { Mladenov, Martin and Globerson, Amir and Kersting, Kristian}, title = {Lifted Message Passing as Reparametrization of Graphical Models}, booktitle = {In Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence (UAI)}, year = {2014}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/MlGlKeUAI14.pdf} } - M. Mladenov, A. Globerson, and K. Kersting: Efficient lifting of map lp relaxations using k-locality. In Proceedings of the 17th international conference on artificial intelligence and statistics (aistats) in journal of machine learning research (jmlr) workshop & conference proceedings series, 33, 2014. [Bibtex]
@InProceedings{ MlGlKeAISTATS14, author = {Mladenov, Martin and Globerson, Amir and Kersting, Kristian}, title = {Efficient Lifting of MAP LP Relaxations Using k-Locality}, booktitle = {Proceedings of the 17th International Conference on Artificial Intelligence and Statistics (AISTATS) in Journal of Machine Learning Research (JMLR) Workshop & Conference Proceedings Series}, year = {2014}, volume = {33}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/MlGlKeAISTATS14.pdf} } - G. Martius, L. Jahn, H. Hauser, and Verena V.~Hafner: Self-exploration of the stumpy robot with predictive information maximization. In Proc.\ from animals to animats, sab 2014, 8575, 32-42, Springer, 2014. [Bibtex]
@InProceedings{ MartiusJahnHauserHafner2014:Stumpy, title = {Self-Exploration of the Stumpy Robot with Predictive Information Maximization}, author = {Georg Martius and Luisa Jahn and Helmut Hauser and Verena V.~Hafner}, booktitle = {Proc.\ From Animals to Animats, SAB 2014}, year = {2014}, publisher = {Springer}, series = {LNCS}, volume = {8575}, pages = {32-42}, editor = {del Pobil, AngelP. and Chinellato, Eris and Martinez-Martin, Ester and Hallam, John and Cervera, Enric and Morales, Antonio}, keywords = {Self-exploration; intrinsic motivation; robot control; information theory; dynamical systems; learning}, file = {MartiusJahnHauserHafner2014:Stumpy.pdf:http\://robot.informatik.uni-leipzig.de/research/publications/2014/MartiusJahnHauserHafner2014:Stumpy.pdf:PDF}, pdf = {http://robot.informatik.uni-leipzig.de/research/publications/2014/MartiusJahnHauserHafner2014:Stumpy.pdf}, comment = {best paper award} } - G. Martius, R. Der, and M. J. Herrmann: Robot learning by guided self-organization. In Guided self-organization: inception, 9, 223-260, Springer Berlin Heidelberg, 2014. [Bibtex]
@InCollection{ MartiusDerHerrmann14, title = {Robot Learning by Guided Self-Organization}, author = {Martius, Georg and Der, Ralf and Herrmann, J. Michael}, booktitle = {Guided Self-Organization: Inception}, publisher = {Springer Berlin Heidelberg}, year = {2014}, editor = {Prokopenko, Mikhail}, pages = {223-260}, series = {Emergence, Complexity and Computation}, volume = {9}, doi = {10.1007/978-3-642-53734-9_8}, isbn = {978-3-642-53733-2}, url = {http://dx.doi.org/10.1007/978-3-642-53734-9_8} } - R. Martín-Martín and O. Brock: Online Interactive Perception of Articulated Objects with Multi-Level Recursive Estimation Based on Task-Specific Priors. In Proceedings of the 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2014. [Bibtex]
@InProceedings{ martin-martin_online_2014, address = {Chicago, Illinois, USA}, title = {Online {Interactive} {Perception} of {Articulated} {Objects} with {Multi}-{Level} {Recursive} {Estimation} {Based} on {Task}-{Specific} {Priors}}, url = {http://www.robotics.tu-berlin.de/fileadmin/fg170/Publikationen_pdf/IROS14_0282_RobertoMM.pdf}, booktitle = {Proceedings of the 2014 {IEEE}/{RSJ} {International} {Conference} on {Intelligent} {Robots} and {Systems} ({IROS})}, author = {Martín-Martín, Roberto and Brock, Oliver}, year = {2014}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/IROS14_0282_RobertoMM.pdf} } - K. Kersting, M. Mladenov, R. Garnett, and M. Grohe: Power iterated color refinement. In Proceedings of the twenty-eighth aaai conference on artificial intelligence (aaai-14), AAAI Press, 2014. [Bibtex]
@InProceedings{ KeMlGaGr14, author = {Kersting, Kristian and Mladenov, Martin and Garnett, Roman and Grohe, Martin}, title = {Power Iterated Color Refinement}, booktitle = {Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI-14)}, year = {2014}, editor = {Carla Brodley and Peter Stone}, publisher = {AAAI Press}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/KeMlGaGr14.pdf} } - S. M. Kazemi, Buchman David, K. Kersting, S. Natarajan, and D. Poole: Relational logistic regression. In In proceedings of the international conference on principles of knowledge representation and reasoning (kr), 2014. [Bibtex]
@InProceedings{ KaBuKeNaPo14, author = {Kazemi, Seyed Mehran and Buchman, David, and Kersting, Kristian and Natarajan, Sriraam and Poole, David}, title = {Relational Logistic Regression}, booktitle = {In Proceedings of the International Conference on Principles of Knowledge Representation and Reasoning (KR)}, year = {2014}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/relational_logistic_regression.pdf} } - B. Mokbel, B. Paassen, and B. Hammer: Efficient adaptation of structure metrics in prototype-based classification. In Artificial neural networks and machine learning – ICANN 2014 – 24th international conference on artificial neural networks, hamburg, germany, september 15-19, 2014. proceedings, 8681, 571-578, Springer, 2014. [Bibtex]
@InProceedings{ ICANN2014-MokPaasHam-EfficientAdaptation, author = {Mokbel, Bassam and Paassen, Benjamin and Hammer, Barbara}, title = {Efficient Adaptation of Structure Metrics in Prototype-Based Classification}, booktitle = {Artificial Neural Networks and Machine Learning - {ICANN} 2014 - 24th International Conference on Artificial Neural Networks, Hamburg, Germany, September 15-19, 2014. Proceedings}, year = {2014}, pages = {571--578}, url = {http://dx.doi.org/10.1007/978-3-319-11179-7_72}, doi = {10.1007/978-3-319-11179-7_72}, series = {Lecture Notes in Computer Science}, volume = {8681}, publisher = {Springer}, isbn = {978-3-319-11178-0}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/MokbelEtAl2014-ICANN2014-EfficientAdaptiveAlignmentGLVQ-1.pdf} } - S. Gross, B. Mokbel, B. Paassen, B. Hammer, and N. Pinkwart: Example-based feedback provision using structured solution spaces. Int. j. of learning technology, 9, 248-280, 2014. [Bibtex]
@Article{ HUB-CSES/GMPHP14, author = {Gross, S. and Mokbel, B. and Paassen, B. and Hammer, B. and Pinkwart, N.}, title = {Example-based feedback provision using structured solution spaces}, editor = {Uden, L.}, journal = {Int. J. of Learning Technology}, volume = {9}, year = {2014}, number = {3}, pages = {248-280}, doi = {10.1504/IJLT.2014.065752} } - S. Gross, B. Mokbel, B. Hammer, and N. Pinkwart: How to select an example? a comparison of selection strategies in example-based learning. In Intelligent tutoring systems, 8474, 340-347, Springer International Publishing, 2014. [Bibtex]
@InProceedings{ HUB-CSES/GMHP14, title = {How to Select an Example? A Comparison of Selection Strategies in Example-Based Learning}, author = {Gross, Sebastian and Mokbel, Bassam and Hammer, Barbara and Pinkwart, Niels}, booktitle = {Intelligent Tutoring Systems}, publisher = {Springer International Publishing}, year = {2014}, editor = {Trausan-Matu, Stefan and Boyer, KristyElizabeth and Crosby, Martha and Panourgia, Kitty}, pages = {340-347}, series = {Lecture Notes in Computer Science}, volume = {8474}, doi = {10.1007/978-3-319-07221-0_42}, isbn = {978-3-319-07220-3}, keywords = {intelligent tutoring system; example-based learning; programming}, language = {English}, url = {http://dx.doi.org/10.1007/978-3-319-07221-0_42} } - J. Heymann, O. Walter, R. Haeb-Umbach, and B. Raj: Iterative bayesian word segmentation for unspuervised vocabulary discovery from phoneme lattices. In 39th international conference on acoustics, speech and signal processing (icassp 2014), 2014. [Bibtex]
@InProceedings{ HeWaHa2014, title = {Iterative Bayesian Word Segmentation for Unspuervised Vocabulary Discovery from Phoneme Lattices}, author = {Heymann, Jahn and Walter, Oliver and Haeb-Umbach, Reinhold and Raj, Bhiksha}, booktitle = {39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)}, year = { 2014 }, month = {may}, abstract = { "In this paper we present an algorithm for the unsupervised segmentation of a lattice produced by a phoneme recognizer into words. Using a lattice rather than a single phoneme string accounts for the uncertainty of the recognizer about the true label sequence. An example application is the discovery of lexical units from the output of an error-prone phoneme recognizer in a zero-resource setting, where neither the lexicon nor the language model (LM) is known. We propose a computationally efficient iterative approach, which alternates between the following two steps: First, the most probable string is extracted from the lattice using a phoneme LM learned on the segmentation result of the previous iteration. Second, word segmentation is performed on the extracted string using a word and phoneme LM which is learned alongside the new segmentation. We present results on lattices produced by a phoneme recognizer on the WSJCAM0 dataset. We show that our approach delivers superior segmentation performance than an earlier approach found in the literature, in particular for higher-order language models. " }, comment = {<a href="http://nt.uni-paderborn.de/public/pubs/2014/HeWaHa2014_Poster.pdf">[Poster]</a>}, url = {http://nt.uni-paderborn.de/public/pubs/2014/HeWaHa2014.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/HeWaHa2014.pdf} } - M. Grohe, K. Kersting, M. Mladenov, and E. Selman: Dimension reduction via colour refinement. In Proceedings of the 22nd european symposium on algorithms (esa), 2014. [Bibtex]
@InProceedings{ GrKeMlSe14, year = {2014}, booktitle = {Proceedings of the 22nd European Symposium on Algorithms (ESA)}, title = {Dimension Reduction via Colour Refinement}, author = { Grohe, Martin and Kersting, Kristian and Mladenov, Martin and Selman, Erkal}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/GrKeMlSe14.pdf} } - B. Mokbel, B. Paassen, and B. Hammer: Adaptive distance measures for sequential data. In 22th european symposium on artificial neural networks, computational intelligence and machine learning, ESANN 2014, bruges, belgium, april 23-25, 2014, 265-270, i6doc.com, 2014. [Bibtex]
@InProceedings{ ESANN2014-MokPaasHam-AdaptiveDistance, author = {Mokbel, Bassam and Paassen, Benjamin and Hammer, Barbara}, title = {Adaptive distance measures for sequential data}, booktitle = {22th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, {ESANN} 2014, Bruges, Belgium, April 23-25, 2014}, pages = {265-270}, year = {2014}, editor = {Michel Verleysen}, publisher = {i6doc.com}, url = {http://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2014-82.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/MokbelEtAl2014-ESANN2014-AdaptiveAlignmentGLVQ-1} } - M. Kümmerer, L. Theis, and Matthias Bethge: Deep gaze I: boosting saliency prediction with feature maps trained on imagenet. Corr, abs/1411.1045, 2014. [Bibtex]
@Article{ DBLP:journals/corr/KummererTB14, author = {Matthias K{\"{u}}mmerer and Lucas Theis and Matthias Bethge}, title = {Deep Gaze {I:} Boosting Saliency Prediction with Feature Maps Trained on ImageNet}, journal = {CoRR}, volume = {abs/1411.1045}, year = {2014}, url = {http://arxiv.org/abs/1411.1045}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/1411.1045v2.pdf} } - M. Jänicke, B. Sick, P. Lukowicz, and D. Bannach: Self-adapting multi-sensor systems: a concept for self-improvement and self-healing techniques. In Self-adaptive and self-organizing systems workshops (sasow), 2014 ieee eighth international conference on, 128-136, 2014. [Bibtex]
@InProceedings{ 7056368, author = {Jänicke, M. and Sick, B. and Lukowicz, P. and Bannach, D.}, booktitle = {Self-Adaptive and Self-Organizing Systems Workshops (SASOW), 2014 IEEE Eighth International Conference on}, title = {Self-Adapting Multi-sensor Systems: A Concept for Self-Improvement and Self-Healing Techniques}, year = {2014}, pages = {128-136}, keywords = {health care;mobile computing;probability;sensor fusion;activity recognition system;medical care;organic computing principle;probabilistic model;self-adapting classification system;self-adapting multisensor system;self-healing technique;self-improvement technique;Adaptation models;Intelligent sensors;Monitoring;Sensor phenomena and characterization;Sensor systems;Training data}, doi = {10.1109/SASOW.2014.22}, month = {Sept}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/15-sick-paper.pdf} } - N. A. Vien and M. Toussaint: Model-based relational rl when object existence is partially observable. In Proc. of the int. conf. on machine learning (icml 2014), 2014. [Bibtex]
@InProceedings{ 14-vien-ICML, key = "ICML", author = "Ngo Anh Vien and Marc Toussaint", title = "Model-Based Relational RL When Object Existence is Partially Observable", booktitle = icml # " (ICML 2014)", year = "2014", url = {https://ipvs.informatik.uni-stuttgart.de/mlr/marc/publications/14-vien-ICML.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/14-vien-ICML.pdf} } - S. Otte, J. Kulick, M. Toussaint, and O. Brock: Entropy based strategies for physical exploration of the environment’s degrees of freedom. In Proc. of the int. conf. on intelligent robots and systems (iros 2014), 2014. [Bibtex]
@InProceedings{ 14-otte-IROS, key = "IROS", author = "S. Otte and J. Kulick and M. Toussaint and O. Brock", title = "Entropy Based Strategies for Physical Exploration of the Environment's Degrees of Freedom", booktitle = iros # " (IROS 2014)", year = "2014", url = {https://ipvs.informatik.uni-stuttgart.de/mlr/marc/publications/14-otte-IROS.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/14-otte-IROS.pdf} } - J. Kulick, R. Lieck, and J. Kulick: Active Learning of Hyperparameters: An Expected Cross Entropy Criterion for Active Model Selection. e-Print arXiv:1409.7552, 2014. [Bibtex]
@Misc{ 14-kulick-MaxCE, key = "MaxCE", author = "Johannes Kulick and Robert Lieck and Johannes Kulick", year = "2014", title = "{{Active Learning of Hyperparameters: An Expected Cross Entropy Criterion for Active Model Selection}}", howpublished = "e-Print arXiv:1409.7552", url = {http://www.arXiv.org/abs/1409.7552}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/1409.7552v1.pdf} }
2013
- K. Zahedi and N. Ay: Quantifying morphological computation. Entropy, 15, 1887-1915, 2013. [Bibtex]
@Article{ Zahedi2013Quantifying-Morphological-Computation, author = {Zahedi, Keyan and Ay, Nihat}, journal = {Entropy}, number = {5}, pages = {1887--1915}, title = {Quantifying Morphological Computation}, volume = {15}, year = {2013} } - O. Walter, J. Schmalenstroer, and Reinhold Haeb-Umbach: A novel initialization method for unsupervised learning of acoustic patterns in speech. 2013. [Bibtex]
@TechReport{ WaScHa13, title = "A Novel Initialization Method for Unsupervised Learning of Acoustic Patterns in Speech", author = "Oliver Walter and Joerg Schmalenstroer and Reinhold Haeb-Umbach", institution = "Department of Communications Engineering", number = "FGNT-2013-01", year = "2013", abstract = "In this paper we present a novel initialization method for unsupervised learning of acoustic patterns in recordings of continuous speech. The pattern discovery task is solved by dynamic time warping whose performance we improve by a smart starting point selection. This enables a more accurate discovery of patterns compared to conventional approaches. After graph-based clustering the patterns are employed for training hidden Markov models for an unsupervised speech acquisition. By iterating between model training and decoding in an EM-like framework the word accuracy is continuously improved. On the TIDIGITS corpus we achieve a word error rate of about 13\% by the proposed unsupervised pattern discovery approach, which neither assumes knowledge of the acoustic units nor of the labels of the training data.", pdf = {../wp-content/papercite-data/pdfs/2013 Haeb-Umbach 3 A_Novel_Initialization_Method_For_Unsupervised_Learning_Of_Acoustic_Patterns_in_Speech_TR.pdf} } - O. Walter, R. Haeb-Umbach, Sourish Chaudhuri, and B. Raj: Unsupervised word discovery from phonetic input using nested pitman-yor language modeling. ICRA Workshop on Autonomous Learning, 2013. [Bibtex]
@Misc{ Walter2013, author = "Oliver Walter and Reinhold Haeb-Umbach and Sourish Chaudhuri and Bhiksha Raj", title = "Unsupervised Word Discovery from Phonetic Input Using Nested Pitman-Yor Language Modeling", year = "2013", abstract = "In this paper we consider the unsupervised word discovery from phonetic input. We employ a word segmentation algorithm which simultaneously develops a lexicon, i.e., the transcription of a word in terms of a phone sequence, learns a n-gram language model describing word and word sequence probabilities, and carries out the segmentation itself. The underlying statistical model is that of a Pitman-Yor process, a concept known from Bayesian non-parametrics, which allows for an a priori unknown and unlimited number of different words. Using a hierarchy of Pitman-Yor processes, language models of different order can be employed and nesting it with another hierarchy of Pitman-Yor processes on the phone level allows for backing off unknown word unigrams by phone m-grams. We present results on a large-vocabulary task, assuming an error-free phone sequence is given. We finish by discussing options how to cope with noisy phone sequences.", howpublished = "ICRA Workshop on Autonomous Learning", pdf = {../wp-content/papercite-data/pdfs/2013 Haeb-Umbach 4 Unsupervised_Word_Discovery_from_Phonetic_Input_Using_Nested_Pitman-Yor_Language_Modeling.pdf} } - O. Walter, T. Korthals, R. Haeb-Umbach, and B. Raj: A hierarchical system for word discovery exploiting dtw-based initialization. In Proc. asru, 2013. [Bibtex]
@InProceedings{ WaKoHaRa13, author = "Oliver Walter and Timo Korthals and Reinhold Haeb-Umbach and Bhiksha Raj", title = "A Hierarchical System for Word Discovery Exploiting DTW-Based Initialization", booktitle = "Proc. ASRU", address = "Olomouc, Czech Republic", year = "2013", abstract = "Discovering the linguistic structure of a language solely from spoken input asks for two steps: phonetic and lexical discovery. The first is concerned with identifying the categorical subword unit inventory and relating it to the underlying acoustics, while the second aims at discovering words as repeated patterns of subword units. The hierarchical approach presented here accounts for classification errors in the first stage by modelling the pronunciation of a word in terms of subword units probabilistically: a hidden Markov model with discrete emission probabilities, emitting the observed subword unit sequences. We describe how the system can be learned in a completely unsupervised fashion from spoken input. To improve the initialization of the training of the word pronunciations, the output of a dynamic time warping based acoustic pattern discovery system is used, as it is able to discover similar temporal sequences in the input data. This improved initialization, using only weak supervision, has led to a 40\% reduction in word error rate on a digit recognition task.", pdf = {../wp-content/papercite-data/pdfs/2013 Haeb-Umbach 1 A_HIERARCHICAL_SYSTEM_FOR_WORD_DISCOVERY_EXPLOITING_DTW-BASED_INITIALIZATION.pdf} } - C. Wirth and J. Fürnkranz: Learning from trajectory-based action preferences. In Proceedings of the icra 2013 workshop on autonomous learning, To be published, 2013. [Bibtex]
@InProceedings{ TrajBasedActionPrefs, author = {Wirth, Christian and F{\"{u}}rnkranz, Johannes}, month = may, title = {Learning from Trajectory-Based Action Preferences}, booktitle = {Proceedings of the ICRA 2013 Workshop on Autonomous Learning}, year = {2013}, location = {Karslruhe}, note = {To be published} } - F. Pasemann: Self-regulating neurons in the sensorimotor loop. In Advances in computational intelligence, 7902, 481-491, Springer Berlin Heidelberg, 2013. [Bibtex]
@InCollection{ SRN-001, title = {Self-regulating Neurons in the Sensorimotor Loop}, author = {Pasemann, Frank}, year = {2013}, booktitle = {Advances in Computational Intelligence}, volume = {7902}, series = {Lecture Notes in Computer Science}, editor = {Rojas, Ignacio and Joya, Gonzalo and Gabestany, Joan}, publisher = {Springer Berlin Heidelberg}, pages = {481--491}, pdf = {../wp-content/papercite-data/pdfs/2013 pasemann 3.pdf} } - S. Schulz, S. Ulbrich, T. Asfour, and R. Dillmann: Incremental Construction of Motion Graphs based on Binary SpacePartitioning. In IEEE International Conference on Robotics and Automation (ICRA), 2013. [Bibtex]
@InProceedings{ Schulza2012, author = {S. Schulz and S. Ulbrich and T. Asfour and R. Dillmann}, title = {{Incremental Construction of Motion Graphs based on Binary SpacePartitioning}}, booktitle = {{IEEE International Conference on Robotics and Automation (ICRA)}}, year = {2013} } - P. Weng, R. Busa-Fekete, and E. Hüllermeier: Interactive Q-learning with ordinal rewards and unreliable tutor. In Proceedings ecml/pkdd workshop on reinforcement learning from generalized feedback: beyond numerical rewards, 2013. [Bibtex]
@InCollection{ rlws2, author = {Weng, Paul and Busa-Fekete, Robert and H{\"{u}}llermeier, Eyke}, title = {Interactive {Q}-Learning with Ordinal Rewards and Unreliable Tutor}, booktitle = {Proceedings ECML/PKDD Workshop on Reinforcement learning from Generalized Feedback: Beyond Numerical Rewards}, year = {2013}, address = {Prague} } - R. Busa-Fekete, B. Szörényi, P. Weng, and E. Hüllermeier: Preference-based evolutionary direct policy search. In Proceedings of the ecml/pkdd workshop on reinforcement learning from generalized feedback: beyond numerical rewards, 2013. [Bibtex]
@InCollection{ rlws1, author = {Busa-Fekete, Robert and Sz{\"{o}}r{\'{e}}nyi, Balazs and Weng, Paul and H{\"{u}}llermeier, Eyke}, title = {Preference-based Evolutionary Direct Policy Search}, booktitle = {Proceedings of the ECML/PKDD Workshop on Reinforcement learning from Generalized Feedback: Beyond Numerical Rewards}, year = {2013}, address = {Prague} } - C. W. Rempis, H. Toutounji, and F. Pasemann: Evaluating neuromodulator-controlled stochastic plasticity for learning recurrent neural control networks. In Proceedings of the 5$^{\text{th}}$ international conference on neural computation theory and applications., 2013. [Bibtex]
@InProceedings{ rempis2013mod2, author = {Rempis, Christian W. and Toutounji, Hazem and Pasemann, Frank}, title = {Evaluating Neuromodulator-Controlled Stochastic Plasticity for Learning Recurrent Neural Control Networks}, year = {2013}, booktitle = {Proceedings of the 5$^{\text{th}}$ International Conference on Neural Computation Theory and Applications.}, pdf = {../wp-content/papercite-data/pdfs/2013 pasemann 2.pdf} } - C. Rempis, H. Toutounji, and F. Pasemann: Controlling the learning of behaviors in the sensorimotor loop with neuromodulators in self-monitoring neural networks. ICRA Workshop on Autonomous Learning, 2013. [Bibtex]
@Misc{ rempis2013mod1, author = {Christian Rempis and Hazem Toutounji and Frank Pasemann}, title = {Controlling the Learning of Behaviors in the Sensorimotor Loop with Neuromodulators in Self-Monitoring Neural Networks}, year = {2013}, howpublished = {ICRA Workshop on Autonomous Learning}, pdf = {../wp-content/papercite-data/pdfs/2013 pasemann 1.pdf} } - M. Missura, C. Müstermann, Malte Mauelshagen, M. Schreiber, and S. Behnke: RoboCup 2012 Best Humanoid Award winner NimbRo TeenSize. In Robocup 2012: robot soccer world cup xvi, Springer, to appear, 2013. [Bibtex]
@InProceedings{ RC12_Winner_Humanoid, author = {Marcell Missura and Cedrick Müstermann and Malte Mauelshagen and Michael Schreiber and Sven Behnke}, title = {{RoboCup} 2012 {Best} {Humanoid} {Award} Winner {NimbRo} {TeenSize}}, booktitle = {RoboCup 2012: Robot Soccer World Cup XVI}, year = {2013}, publisher = {Springer}, note = {to appear}, pdf = {../wp-content/papercite-data/pdfs/2013Missura.pdf} } - Q. Li, R. Haschke, and H. Ritter: Two-fingered, tactile-based manipulation of unknown objects. In Rss ws: sensitive robotics, 2013. [Bibtex]
@Conference{ QiangRSS2013WS, title = {Two-fingered, tactile-based manipulation of unknown objects}, booktitle = {RSS WS: Sensitive Robotics}, year = {2013}, month = {June 27}, address = {Berlin, Germany}, author = {Qiang Li and Robert Haschke and Helge Ritter}, pdf = {../wp-content/papercite-data/pdfs/2013 Bielefeld Ritter 5Qiangrssws.pdf} } - Q. Li, C. Schürmann, R. Haschke, and H. Ritter: A control framework for tactile servoing. In Rss 2013, 2013. [Bibtex]
@Conference{ QiangRSS2013, title = {A control framework for tactile servoing}, booktitle = {RSS 2013}, year = {2013}, month = {24/06/2013}, address = {Berlin Germany}, author = {Qiang Li and Carsten Sch{\"u}rmann and Robert Haschke and Helge Ritter}, pdf = {../wp-content/papercite-data/pdfs/2013 Bielefeld Ritter 4Qiangrss.pdf} } - Q. Li, C. Elbrechter, R. Haschke, and H. Ritter: Integrating vision, haptics and proprioception into a feedback controller for in-hand manipulation of unknown objects. Iros2013, IEEE, 2013. [Bibtex]
@InProceedings{ QiangIROS2013, title = {Integrating vision, haptics and proprioception into a feedback controller for in-hand manipulation of unknown objects}, journal = {IROS2013}, year = {2013}, month = {November 3.}, publisher = {IEEE}, address = {Tokyo, Japan}, author = {Qiang Li and Christof Elbrechter and Robert Haschke and Helge Ritter}, pdf = {../wp-content/papercite-data/pdfs/2013 Bielefeld Ritter 3Qiangiros.pdf} } - Q. Li, M. Meier, R. Haschke, Bram Bolder, and H. Ritter: Rotary object dexterous manipulation in hand: a feedback-based method. International journal of mechatronics and automation (ijma), Vol.3, 12, 2013. [Bibtex]
@Article{ QiangIJMA2013, title = {Rotary Object Dexterous Manipulation in Hand: A Feedback-based Method}, journal = {International Journal of Mechatronics and Automation (IJMA)}, volume = {Vol.3}, year = {2013}, pages = {12}, chapter = {36}, author = {Qiang Li and Martin Meier and Robert Haschke and Bram Bolder and Helge Ritter}, pdf = {../wp-content/papercite-data/pdfs/2013 Bielefeld Ritter 2QiangIJMA.pdf} } - Q. Li, R. Haschke, and H. Ritter: Toward autonoumous visual-tactile exploration and manipulation. In Icra2013 ws:interactive perception, IEEE, 2013. [Bibtex]
@Conference{ QiangICRA2013WS, title = {Toward Autonoumous Visual-tactile Exploration and Manipulation}, booktitle = {ICRA2013 WS:Interactive Perception}, year = {2013}, month = {06/05/2013}, publisher = {IEEE}, organization = {IEEE}, address = {Karlsruhe, Germany}, author = {Qiang Li and Robert Haschke and Helge Ritter}, pdf = {../wp-content/papercite-data/pdfs/2013 Bielefeld Ritter 1Qiangicra2013ws.pdf} } - M. Missura and S. Behnke: Omnidirectional capture steps for bipedal walking. In Ieee-ras int. conf. on humanoid robots (humanoids), 2013. [Bibtex]
@InProceedings{ Missura:OmniCaptureSteps, author = {Marcell Missura and Sven Behnke}, title = {Omnidirectional Capture Steps for Bipedal Walking}, booktitle = {IEEE-RAS Int. Conf. on Humanoid Robots (Humanoids)}, year = {2013} } - G. Martius, R. Der, and N. Ay: Information driven self-organization of complex robotic behaviors. Plos one, 8, e63400, Public Library of Science, 2013. [Bibtex]
@Article{ MartiusDerAy2013, author = {Georg Martius and Ralf Der and Nihat Ay}, journal = {PLoS ONE}, publisher = {Public Library of Science}, title = {Information Driven Self-Organization of Complex Robotic Behaviors}, year = {2013}, month = {05}, volume = {8}, pages = {e63400}, number = {5}, doi = {10.1371/journal.pone.0063400} } - G. Martius: Robustness of guided self-organization against sensorimotor disruptions. Advances in complex systems, 16, 1350001, 2013. [Bibtex]
@Article{ Martius2012, author = {Georg Martius}, journal = {Advances in Complex Systems}, title = {Robustness of guided self-organization against sensorimotor disruptions}, year = {2013}, volume = {16}, pages = {1350001}, number = {02n03}, doi = {10.1142/S021952591350001X}, pdf = {http://robot.informatik.uni- leipzig.de/research/publications/2012/martius_robustness_of_gso_12_watermark.pdf}, eprint = {http://www.worldscientific.com/doi/pdf/10.1142/S021952591350001X} } - T. Lang, M. Toussaint, and K. Kersting: Exploration in relational domains for model-based reinforcement learning. Journal of machine learning research, 2013. [Bibtex]
@Article{ LangToussaintKersting13, author = {Tobias Lang and Marc Toussaint and Kristian Kersting}, title = {Exploration in Relational Domains for Model-based Reinforcement Learning}, journal = {Journal of Machine Learning Research}, year = {2013}, pdf = {../wp-content/papercite-data/pdfs/13-lang-toussaint-kersting-JMLR.pdf} } - C. Wirth and J. Fürnkranz: Preference-based reinforcement learning: a preliminary survey. In Proceedings of the ecml/pkdd-13 workshop on reinforcement learning from generalized feedback: beyond numeric rewards, 2013. [Bibtex]
@InProceedings{ jf:PBRL-13-Survey, author = {Wirth, Christian and F{\"{u}}rnkranz, Johannes}, editor = {F{\"{u}}rnkranz, Johannes and H{\"{u}}llermeier, Eyke}, title = {Preference-Based Reinforcement Learning: A Preliminary Survey}, booktitle = {Proceedings of the ECML/PKDD-13 Workshop on Reinforcement Learning from Generalized Feedback: Beyond Numeric Rewards}, year = {2013}, pdf = {http://www.ke.tu-darmstadt.de/events/PBRL-13/papers/10-Wirth.pdf} } - E. Hüllermeier and J. Fürnkranz: Editorial: preference learning and ranking. Machine learning, 93, 185-189, 2013. [Bibtex]
@Article{ jf:MLJ-SI-Preferences-Editorial, author = {H{\"{u}}llermeier, Eyke and F{\"{u}}rnkranz, Johannes}, title = {Editorial: Preference Learning and Ranking}, journal = {Machine Learning}, volume = {93}, number = {2-3}, year = {2013}, pages = {185--189}, pdf = {http://www.springer.com/alert/urltracking.do?id=L35fd080Md1c8edSad2177d} } - C. Wirth and J. Fürnkranz: Epmc: Every visit preference Monte Carlo for reinforcement learning. In Proceedings of the 5th asian conference on machine learning, (acml-13), 29, 483-497, JMLR.org, 2013. [Bibtex]
@InProceedings{ jf:ACML-13, author = {Wirth, Christian and F{\"{u}}rnkranz, Johannes}, editor = {Ong, Cheng Soon and Ho, Tu-Bao}, title = {EPMC: {Every} Visit Preference {Monte Carlo} for Reinforcement Learning}, booktitle = {Proceedings of the 5th Asian Conference on Machine Learning, (ACML-13)}, series = {JMLR Proceedings}, volume = {29}, year = {2013}, pages = {483--497}, publisher = {JMLR.org}, address = {Canberra, ACT, Australia}, pdf = {http://jmlr.org/proceedings/papers/v29/Wirth13.html} } - R. Busa-Fekete, B. Szörényi, P. Weng, W. Cheng, and E. Hüllermeier: Top-k selection based on adaptive sampling of noisy preferences. In Proceedings of the international conference on machine learning (icml-13), 2013. [Bibtex]
@InCollection{ icml13, author = {Busa-Fekete, Robert and Sz{\"{o}}r{\'{e}}nyi, Balazs and Weng, Paul and Cheng, Weiwei and H{\"{u}}llermeier, Eyke}, title = {Top-k Selection based on Adaptive Sampling of Noisy Preferences}, booktitle = {Proceedings of the International Conference on Machine Learning (ICML-13)}, year = {2013}, address = {Atlanta, USA} } - J. Heymann, O. Walter, R. Haeb-Umbach, and B. Raj: Unsupervised word segmentation from noisy input. In Proc. asru, 2013. [Bibtex]
@InProceedings{ HeWaHaRa13, title = "Unsupervised Word Segmentation from Noisy Input", booktitle = "Proc. ASRU", author = "Jahn Heymann and Oliver Walter and Reinhold Haeb-Umbach and Bhiksha Raj", address = "Olomouc, Czech Republic", year = "2013", abstract = "In this paper we present an algorithm for the unsupervised segmentation of a character or phoneme lattice into words. Using a lattice at the input rather than a single string accounts for the uncertainty of the character/phoneme recognizer about the true label sequence. An example application is the discovery of lexical units from the output of an error-prone phoneme recognizer in a zero-resource setting, where neither the lexicon nor the language model is known. Recently a Weighted Finite State Transducer (WFST) based approach has been published which we show to suffer from an issue: language model probabilities of known words are computed incorrectly. Fixing this issue leads to greatly improved precision and recall rates, however at the cost of increased computational complexity. It is therefore practical only for single input strings. To allow for a lattice input and thus for errors in the character/phoneme recognizer, we propose a computationally efficient suboptimal two-stage approach, which is shown to significantly improve the word segmentation performance compared to the earlier WFST approach.", pdf = {../wp-content/papercite-data/pdfs/2013 Haeb-Umbach 2 UNSUPERVISED_WORD_SEGMENTATION_FROM_NOISY_INPUT.pdf} } - F. Hadiji and K. Kersting: Reduce and re–lift: bootstrapped lifted likelihood maximization for map. In In proceedings of the twenty-seventh aaai conference on artificial intelligence (aaai-13), 2013. [Bibtex]
@InProceedings{ hadiji13aaai, author = {F. Hadiji and K. Kersting}, title = {Reduce and Re{--}Lift: Bootstrapped Lifted Likelihood Maximization for MAP}, year = {2013}, booktitle = {In Proceedings of the Twenty-Seventh AAAI Conference on Artificial Intelligence (AAAI-13) }, pdf = {../wp-content/papercite-data/pdfs/2013 Kersting 3 hadiji13aaai.pdf} } - S. Gross, B. Mokbel, B. Hammer, and N. Pinkwart: Towards a domain-independent its middleware architecture. In Proceedings of the 13th ieee international conference on advanced learning technologies (icalt), 408-409, 2013. [Bibtex]
@InProceedings{ GrossEtAl2013b, year = {2013}, booktitle = {Proceedings of the 13th IEEE International Conference on Advanced Learning Technologies (ICALT)}, editor = {Chen, N.-S. and Huang, R. and Kinshuk and Li, Y. and Sampson, D. G.}, author = {Gross, S. and Mokbel, B. and Hammer, B. and Pinkwart, N.}, title = {Towards a Domain-Independent ITS Middleware Architecture}, pages = {408 - 409}, keywords = {intelligent tutoring system, middleware, machine learning}, doi = {10.1109/ICALT.2013.124}, pdf = {http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=6601966} } - S. Gross, B. Mokbel, B. Hammer, and N. Pinkwart: Towards providing feedback to students in absence of formalized domain models. In Artificial intelligence in education, 7926, 644-648, Springer Verlag, 2013. [Bibtex]
@InProceedings{ GrossEtAl2013a, year = {2013}, isbn = {978-3-642-39111-8}, booktitle = {Artificial Intelligence in Education}, volume = {7926}, series = {Lecture Notes in Computer Science}, editor = {Lane, H. Chad and Yacef, Kalina and Mostow, Jack and Pavlik, Philip}, doi = {10.1007/978-3-642-39112-5_79}, title = {Towards Providing Feedback to Students in Absence of Formalized Domain Models}, publisher = {Springer Verlag}, address = {Berlin, Germany}, keywords = {intelligent tutoring systems; feedback provision; machine learning}, author = {Gross, S. and Mokbel, B. and Hammer, B. and Pinkwart, N.}, pages = {644 - 648}, pdf = {http://dx.doi.org/10.1007/978-3-642-39112-5_79} } - D. Fierens, K. Kersting, J. Davis, J. Chen, and M. Mladenov: Pairwise markov logic. In Postproceedings of the 22nd international conference on inductive logic programming (ilp–2012), Springer, 2013. [Bibtex]
@InProceedings{ fierens13ilp, author = {D. Fierens and K. Kersting and J. Davis and J. Chen and M. Mladenov}, title = {Pairwise Markov Logic}, year = {2013}, booktitle = {Postproceedings of the 22nd International Conference on Inductive Logic Programming (ILP{--}2012)}, editor = {F. Riguzzi, F. Zelezny}, publisher = {Springer}, series = {LNCS}, pdf = {../wp-content/papercite-data/pdfs/2013 Kersting 2fierens12ilp_pairwise.pdf} } - R. Der and G. Martius: Behavior as broken symmetry in embodied self- organizing robots. In Advances in artificial life, ecal 2013, 601-608, MIT Press, 2013. [Bibtex]
@InCollection{ DerMartius13, title = {Behavior as broken symmetry in embodied self- organizing robots}, author = {Ralf Der and Georg Martius}, booktitle = {Advances in Artificial Life, ECAL 2013}, publisher = {MIT Press}, year = {2013}, pages = {601-608}, affiliation = {Max Planck Institute for Mathematics in the Sciences}, pdf = {http://robot.informatik.uni-leipzig.de/research/publications/2013/ECAL2013.pdf} } - R. Der and G. Martius: Behavior as broken symmetry in embodied self-organizing robots. In Advances in artificial life, ecal 2013, 601-608, MIT Press, 2013. [Bibtex]
@InCollection{ DerMartius13, author = {Ralf Der and Georg Martius}, affiliation = {Max Planck Institute for Mathematics in the Sciences}, title = {Behavior as broken symmetry in embodied self-organizing robots}, booktitle = {Advances in Artificial Life, ECAL 2013}, year = {2013}, pages = {601-608}, publisher = {MIT Press} } - C. Wirth and J. Fürnkranz: A policy iteration algorithm for learning from preference-based feedback. In Advances in intelligent data analysis xii: 12th international symposium (ida-13), 8207, Springer-Verlag, 2013. [Bibtex]
@InProceedings{ cwIDA13, author = {Wirth, Christian and F{\"{u}}rnkranz, Johannes}, editor = {Tucker, Allan and H{\"{o}}ppner, Frank and Siebes, Arno and Swift, Stephen}, month = oct, title = {A Policy Iteration Algorithm for Learning from Preference-based Feedback}, booktitle = {Advances in Intelligent Data Analysis XII: 12th International Symposium (IDA-13)}, series = {LNCS}, volume = {8207}, year = {2013}, publisher = {Springer-Verlag} } - R. Busa-Fekete, B. Szörényi, P. Weng, W. Cheng, and E. Hüllermeier: Preference-based evolutionary direct policy search. In Proceedings of the icra workshop on autonomous learning, 2013. [Bibtex]
@InProceedings{ BusafeketeEvoPref, author = {Busa-Fekete, Robert and Sz{\"{o}}r{\'{e}}nyi, Balazs and Weng, Paul and Cheng, Weiwei and H{\"{u}}llermeier, Eyke}, title = {Preference-based Evolutionary Direct Policy Search}, booktitle = {Proceedings of the ICRA Workshop on Autonomous Learning}, year = {2013} } - W. Böhmer, S. Grünewälder, Y. Shen, M. Musial, and K. Obermayer: Construction of approximation spaces for reinforcement learning. Journal of machine learning research, 14, 2067-2118, 2013. [Bibtex]
@Article{ Boehmer13a, title = {Construction of Approximation Spaces for Reinforcement Learning}, author = {Wendelin B\"ohmer and Steffen Gr\"unew\"alder and Yun Shen and Marek Musial and Klaus Obermayer}, pages = {2067--2118}, year = {2013}, journal = {Journal of Machine Learning Research}, volume = {14}, month = {July}, abstract = {Linear reinforcement learning (RL) algorithms like least-squares temporal difference learning (LSTD) require basis functions that span approximation spaces of potential value functions. This article investigates methods to construct these bases from samples. We hypothesize that an ideal approximation spaces should encode diffusion distances and that slow feature analysis (SFA) constructs such spaces. To validate our hypothesis we provide theoretical statements about the LSTD value approximation error and induced metric of approximation spaces constructed by SFA and the state-of-the-art methods Krylov bases and proto-value functions (PVF). In particular, we prove that SFA minimizes the average (over all tasks in the same environment) bound on the above approximation error. Compared to other methods, SFA is very sensitive to sampling and can sometimes fail to encode the whole state space. We derive a novel importance sampling modification to compensate for this effect. Finally, the LSTD and least squares policy iteration (LSPI) performance of approximation spaces constructed by Krylov bases, PVF, SFA and PCA is compared in benchmark tasks and a visual robot navigation experiment (both in a realistic simulation and with a robot). The results support our hypothesis and suggest that (i) SFA provides subspace-invariant features for MDPs with self-adjoint transition operators, which allows strong guarantees on the approximation error, (ii) the modified SFA algorithm is best suited for LSPI in both discrete and continuous state spaces and (iii) approximation spaces encoding diffusion distances facilitate LSPI performance.}, pdf = {../wp-content/papercite-data/pdfs/Boehmer13 - Construction of Approximation Spaces for Reinforcement Learning.pdf} } - N. Ay and K. Zahedi: An information theoretic approach to intention and deliberative decision-making of embodied systems. In Advances in cognitive neurodynamics iii, Springer, 2013. [Bibtex]
@InCollection{ Ay2013An-Information-Theoretic-Approach, address = {Heidelberg}, author = {Ay, Nihat and Zahedi, Keyan}, booktitle = {Advances in cognitive neurodynamics III}, publisher = {Springer}, title = {An Information Theoretic Approach to Intention and Deliberative Decision-Making of Embodied Systems}, year = {2013} } - B. Ahmadi, K. Kersting, M. Mladenov, and S. Natarajan: Exploiting symmetries for scaling loopy belief propagation and relational training. Machine learning journal, 92, 91{–}132, 2013. [Bibtex]
@Article{ ahmadi2013mlj, author = {B. Ahmadi and K. Kersting and M. Mladenov and S. Natarajan}, title = {Exploiting Symmetries for Scaling Loopy Belief Propagation and Relational Training}, journal = {Machine Learning Journal}, year = {2013}, volume = {92}, number = {1}, pages = {91{--}132}, month = {July}, pdf = {../wp-content/papercite-data/pdfs/2013 Kersting 1ahmadi13mlj.pdf} } - N. A. Vien and M. Toussaint: Reasoning with uncertainties over existence of objects. AAAI Technical Report FS-13-02, 2013. [Bibtex]
@Misc{ 13-vien-AAAIws, key = "AAAIws", year = "2013", title = "Reasoning with Uncertainties Over Existence Of Objects", author = "Ngo Anh Vien and Marc Toussaint", howpublished = "AAAI Technical Report FS-13-02", url = {https://ipvs.informatik.uni-stuttgart.de/mlr/marc/publications/13-vien-AAAIws.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/13-vien-AAAIws.pdf} } - M. Toussaint, T. Lang, and N. Jetchev: Kognitive robotik — herausforderungen an unser verständnis natürlicher umgebungen. Automatisierungstechnik, 2013. [Bibtex]
@Article{ 13-toussaint-AT, key = "AT", author = "Marc Toussaint and Tobias Lang and Nikolay Jetchev", title = "Kognitive Robotik -- Herausforderungen an unser Verst{\"a}ndnis nat{\"u}rlicher Umgebungen", journal = "Automatisierungstechnik", year = "2013", url = {https://ipvs.informatik.uni-stuttgart.de/mlr/marc/publications/13-toussaint-AT.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/13-toussaint-AT.pdf} } - Werner von and K. Behrend: Prinzipien neuronaler informationsverarbeitung. Manuscript, 2013. [Bibtex]
@Misc{ 13-seelen, title = "Prinzipien neuronaler Informationsverarbeitung", author = "{Werner von} Seelen and Konstantin Behrend", howpublished = "Manuscript", year = "2013", pdf = {http://autonomous-learning.org/wp-content/uploads/Paper-vonSeelen.pdf} } - A. Orthey, M. Toussaint, and N. Jetchev: Optimizing motion primitives to make symbolic models more predictive. In Proc. of the ieee int. conf. on robotics \& automation (icra 2013), 2013. [Bibtex]
@InProceedings{ 13-orthey-ICRA, key = "ICRA", author = "Andreas Orthey and Marc Toussaint and Nikolay Jetchev", title = "Optimizing Motion Primitives to Make Symbolic Models More Predictive", booktitle = icra # " (ICRA 2013)", year = "2013", url = {BASEURL/13-orthey-ICRA.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/13-orthey-ICRA.pdf} } - J. Kulick, M. Toussaint, T. Lang, and M. Lopes: Active learning for teaching a robot grounded relational symbols. In Proc. of the int. joint conf. on artificial intelligence (ijcai 2013), 2013. [Bibtex]
@InProceedings{ 13-kulick-IJCAI, key = "IJCAI", year = "2013", title = "Active Learning for Teaching a Robot Grounded Relational Symbols", author = "Johannes Kulick and Marc Toussaint and Tobias Lang and Manuel Lopes", booktitle = ijcai # " (IJCAI 2013)", url = {https://ipvs.informatik.uni-stuttgart.de/mlr/marc/publications/13-kulick-IJCAI.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/13-kulick-IJCAI.pdf} } - N. Jetchev, T. Lang, and M. Toussaint: Learning grounded relational symbols from continuous data for abstract reasoning. ICRA Workshop on Autonomous Learning, 2013. [Bibtex]
@Misc{ 13-jetchev-ICRAws, key = "ICRAws", year = "2013", title = "Learning Grounded Relational Symbols from Continuous Data for Abstract Reasoning", author = "Nikolay Jetchev and Tobias Lang and Marc Toussaint", howpublished = "ICRA Workshop on Autonomous Learning", url = {http://ipvs.informatik.uni-stuttgart.de/mlr/marc/publications/13-jetchev-ICRAws.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/13-jetchev-ICRAws.pdf} }
2012
- C. Wirth and J. Fürnkranz: First steps towards learning from game annotations. In Workshop proceedings – preference learning: problems and applications in ai at ecai 2012, 53-58, 2012. [Bibtex]
@InProceedings{ Wirth12GameAnnon, author = {Wirth, Christian and F{\"{u}}rnkranz, Johannes}, month = aug, title = {First Steps Towards Learning from Game Annotations}, booktitle = {Workshop Proceedings - Preference Learning: Problems and Applications in AI at ECAI 2012}, year = {2012}, pages = {53-58}, location = {Montpellier}, pdf = {http://www.ke.tu-darmstadt.de/events/PL-12/papers/11-wirth.pdf} } - C. Wirth and J. Fürnkranz: First steps towards learning from game annotations. In Workshop proceedings – preference learning: problems and applications in ai at ecai 2012, 53-58, 2012. [Bibtex]
@InProceedings{ Wirth12aGameAnnon, author = {Wirth, Christian and Fürnkranz, Johannes}, title = {First Steps Towards Learning from Game Annotations}, booktitle = {Workshop Proceedings - Preference Learning: Problems and Applications in AI at ECAI 2012}, year = {2012}, pages = {53-58}, month = aug, location = {Montpellier}, pdf = {http://www.ke.tu-darmstadt.de/events/PL-12/papers/11-wirth.pdf} } - U. van Hengel, Y. Sandamirskaya, S. Schneegans, and S. G: A neural-dynamic architecture for flexible spatial language: intrinsic frames, the term “between”, and autonomy. In 21st ieee international symposium on robot and human interactivecommunication (ro-man) 2012, 2012. [Bibtex]
@Conference{ vanHengelEtAl2012, author = {van Hengel, U and Sandamirskaya, Y and Schneegans, S and Sch\"oner G}, title = {A neural-dynamic architecture for flexible spatial language: intrinsic frames, the term “between”, and autonomy}, booktitle = {21st IEEE International Symposium on Robot and Human InteractiveCommunication (Ro-Man) 2012}, year = {2012}, pdf = {http://sandamirskaya.eu/resources/submissionRoMan2012.pdf} } - S. Ulbrich, M. Bechtel, T. Asfour, and R. Dillmann: Learning robot dynamics with kinematic bézier maps. In Ieee/rsj international conference on intelligent robots and systems (iros), 2012. [Bibtex]
@InProceedings{ Ulbrich2012cc, author = {S. Ulbrich and M. Bechtel and T. Asfour and R. Dillmann}, title = {Learning Robot Dynamics with Kinematic Bézier Maps}, booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, year = {2012}, pdf = {http://his.anthropomatik.kit.edu/pdf_humanoids/Ulbrich2012c.pdf} } - S. Ulbrich, V. Ruiz, T. Asfour, C. Torras, and R. Dillmann: Kinematic bézier maps. Ieee transactions on systems, man, and cybernetics, 42, 1215-1230, 2012. [Bibtex]
@Article{ Ulbrich2012bb, author = {S. Ulbrich and V. Ruiz and T. Asfour and C. Torras and R. Dillmann}, title = {Kinematic Bézier Maps}, journal = {IEEE Transactions on Systems, Man, and Cybernetics}, year = {2012}, volume = {42}, pages = {1215-1230}, number = {4}, pdf = {http://his.anthropomatik.kit.edu/pdf_humanoids/Ulbrich2012b.pdf} } - S. Ulbrich, V. Ruiz, T. Asfour, C. Torras, and R. Dillmann: General kinematics decomposition without intermediate markers. Ieee transactions on neural networks and learning systems, 23, 620-630, 2012. [Bibtex]
@Article{ Ulbrich2012aa, author = {S. Ulbrich and V. Ruiz and T. Asfour and C. Torras and R. Dillmann}, title = {General Kinematics Decomposition without Intermediate Markers}, journal = {IEEE Transactions on Neural Networks and Learning Systems}, year = {2012}, volume = {23}, pages = {620-630}, number = {4}, pdf = {http://his.anthropomatik.kit.edu/pdf_humanoids/Ulbrich2012a.pdf} } - N. Pinkwart and B. Hammer: Towards learning feedback in intelligent tutoring systems by clustering spaces of student solutions. In Proceedings of the 25th international conference of the florida artificial intelligence research society (flairs), 572, AAAI, 2012. [Bibtex]
@InProceedings{ TUC-HCISa/PH12, author = {N. Pinkwart and B. Hammer}, title = {Towards Learning Feedback in Intelligent Tutoring Systems by Clustering Spaces of Student Solutions}, booktitle = {Proceedings of the 25th International Conference of the Florida Artificial Intelligence Research Society (FLAIRS)}, year = {2012}, editor = {G. M. Youngblood and P. McCarthy}, pages = {572}, address = {Marco Island, FL, USA}, publisher = {AAAI}, pdf = {http://hcis.in.tu-clausthal.de/pubs/2012/flairs/towards_learning_feedback_in_intelligent_tutoring_systems_by_clustering_spaces_of_student_solutions.pdf} } - S. Gross, X. Zhu, B. Hammer, and N. Pinkwart: Cluster based feedback provision strategies in intelligent tutoring systems. In Proceedings of the 11th international conference on intelligent tutoring systems (its), 7315, 699-700, Springer Verlag, 2012. [Bibtex]
@InProceedings{ TUC-HCISa/GZHP12, author = {Gross, S. and Zhu, X. and Hammer, B. and Pinkwart, N.}, title = {Cluster Based Feedback Provision Strategies in Intelligent Tutoring Systems}, booktitle = {Proceedings of the 11th International Conference on Intelligent Tutoring Systems (ITS)}, year = {2012}, editor = {Cerri, Stefano and Clancey, William and Papadourakis, Giorgos and Panourgia, Kitty}, volume = {7315}, series = {Lecture Notes in Computer Science}, pages = {699 - 700}, address = {Berlin, Germany}, publisher = {Springer Verlag}, pdf = {http://hcis.in.tu-clausthal.de/pubs/2012/its/cluster_based_feedback_provision_strategies_in_intelligent_tutoring_systems.pdf} } - S. Gross, B. Mokbel, B. Hammer, and N. Pinkwart: Feedback provision strategies in intelligent tutoring systems based on clustered solution spaces. In Delfi 2012: die 10. e-learning fachtagung informatik, 27-38, Köllen, 2012. [Bibtex]
@InProceedings{ TUC-HCISa/GMHP12, author = {Gross, S. and Mokbel, B. and Hammer, B. and Pinkwart, N.}, title = {Feedback Provision Strategies in Intelligent Tutoring Systems Based on Clustered Solution Spaces}, booktitle = {DeLFI 2012: Die 10. e-Learning Fachtagung Informatik}, year = {2012}, editor = {Desel, J\"org and Haake, Joerg M. and Spannagel, Christian}, pages = {27-38}, address = {Hagen, Germany}, publisher = {K\"ollen}, isbn = {978-3885796015}, pdf = {http://hcis.in.tu-clausthal.de/pubs/2012/delfi/feedback_provision_strategies_in_intelligent_tutoring_systems_based_on_clustered_solution_spaces.pdf} } - B. Mokbel, S. Gross, M. Lux, N. Pinkwart, and B. Hammer: How to quantitatively compare data dissimilarities for unsupervised machine learning?. In Annpr, 7477, 1-13, Springer, 2012. [Bibtex]
@InProceedings{ TUC-HCIS/aMGLPH12, author = {Mokbel, B. and Gross, S. and Lux, M. and Pinkwart, N. and Hammer, B.}, title = {How to Quantitatively Compare Data Dissimilarities for Unsupervised Machine Learning?}, booktitle = {ANNPR}, year = {2012}, editor = {Mana, Nadia and Schwenker, Friedhelm and Trentin, Edmondo}, volume = {7477}, series = {Lecture Notes in Computer Science}, pages = {1-13}, publisher = {Springer}, pdf = {http://hcis.in.tu-clausthal.de/pubs/2012/annpr/how_to_quantitatively_compare_data_dissimilarities_for_unsupervised_machine_learning.pdf} } - L. Theis, R. Hosseini, and M. Bethge: Mixtures of conditional gaussian scale mixtures applied to multiscale image representations. Plos one, 7, Public Library of Science, 2012. [Bibtex]
@Article{ theis2012aa, author = {L. Theis and R. Hosseini and M. Bethge}, title = {Mixtures of Conditional Gaussian Scale Mixtures Applied to Multiscale Image Representations}, journal = {PLoS ONE}, year = {2012}, volume = {7}, number = {7}, month = {Jul}, doi = {10.1371/journal.pone.0039857}, keywords = {natural image statistics, gaussian scale mixtures, random fields}, publisher = {Public Library of Science}, pdf = {http://autonomous-learning.org/wp-content/uploads/theis12a.pdf} } - L. Theis, J. Sohl-Dickstein, and M. Bethge: Training sparse natural image models with a fast Gibbs sampler of an extended state space. In Advances in neural information processing systems 25, 2012. [Bibtex]
@InProceedings{ the2012dd, author = {L. Theis and J. Sohl-Dickstein and M. Bethge}, title = {{Training sparse natural image models with a fast Gibbs sampler of an extended state space}}, booktitle = {Advances in Neural Information Processing Systems 25}, year = {2012}, month = {Nov}, keywords = {natural image statistics, ica, overcompleteness}, pdf = {http://books.nips.cc/papers/files/nips25/NIPS2012_0540.pdf} } - S. Schneegans and G. Schöner: A neural mechanism for coordinate transformation predicts pre-saccadic remapping. Biological cybernetics, 1-21, Springer, 2012. [Bibtex]
@Article{ SchneegansSchoner2012, author = {Schneegans, S. and Sch{\"o}ner, G.}, title = {A neural mechanism for coordinate transformation predicts pre-saccadic remapping}, journal = {Biological cybernetics}, year = {2012}, pages = {1--21}, publisher = {Springer}, pdf = {http://autonomous-learning.org/wp-content/uploads/schoener.pdf} } - W. Samek, K. Müller, M. Kawanabe, and C. Vidaurre: Brain-computer interfacing in discriminative and stationary subspaces. In Conf proc ieee eng med biol soc, 2012. [Bibtex]
@InProceedings{ SamMueKawVid12, author = {Samek, Wojciech and M{\"u}ller, Klaus-Robert and Kawanabe, Motoaki and Vidaurre, Carmen}, title = {Brain-Computer Interfacing in Discriminative and Stationary Subspaces}, booktitle = {Conf Proc IEEE Eng Med Biol Soc}, year = {2012}, file = {SamEMBS12.pdf:http\://www.user.tu-berlin.de/wojwoj/pdf/SamEMBS12.pdf:PDF}, folder = {BBCI}, pdf = {http://autonomous-learning.org/wp-content/uploads/SamMüller12.pdf} } - M. Richter, Y. Sandamirskaya, and G. Schöner: A robotic architecture for action selection and behavioral organization inspired by human cognition. In Ieee/rsj international conference on intelligent robots and systems, iros, 2012. [Bibtex]
@InProceedings{ RichterSandamirskayaSchoner2012, author = {Richter, M. and Sandamirskaya, Y. and Sch\"oner, G}, title = {A robotic architecture for action selection and behavioral organization inspired by human cognition}, booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS}, year = {2012}, pdf = {http://sandamirskaya.eu/resources/RichterSandamirskayaSchoner2012_IROS.pdf} } - G. Martius and J. Herrmann: Variants of guided self-organization for robot control. Theory in biosci., 131, 129-137, Springer Berlin / Heidelberg, 2012. [Bibtex]
@Article{ martiusherrmann:variantsofgso12, author = {Martius, Georg and Herrmann, J.~Michael}, affiliation = {Bernstein Center for Computational Neuroscience and Max Planck Institute for Dynamics and Self-Organization, Bunsenstr. 10, 37073 Göttingen, Germany}, title = {Variants of guided self-organization for robot control}, journal = {Theory in Biosci.}, publisher = {Springer Berlin / Heidelberg}, issn = {1431-7613}, pages = {129-137}, volume = 131, number = 3, year = 2012, pdf = {http://robot.informatik.uni- leipzig.de/research/publications/2012/martiusherrmann_variantsofgso_12_watermark.pdf}, doi = {10.1007/s12064-011-0141-0} } - G. Martius: Robustness of guided self-organization against sensorimotor disruptions. Advances in complex systems, accepted 15.Oct 2012, 2012. [Bibtex]
@Article{ Martius:RobustnessOfGSO2012, author = {Georg Martius}, journal = {Advances in Complex Systems}, title = {Robustness of guided self-organization against sensorimotor disruptions}, year = {2012}, note = {accepted 15.Oct 2012}, pdf = {http://autonomous-learning.org/wp-content/uploads/martius_robustness_of_gso_12_watermark.pdf} } - Q. Li, R. Haschke, B. Bolder, and Helge Ritter: Grasp point optimization by online exploration of unknown object surface. 12th ieee-ras intl conf on humanoid robots, 2012. [Bibtex]
@InProceedings{ LiHaschkeBolderRitter, title = {Grasp Point Optimization by Online Exploration of Unknown Object Surface}, year = {2012}, address = {Osaka, Japan}, month = {29/11/2012}, author = {Qiang Li and Robert Haschke and Bram Bolder and Helge Ritter}, journal = {12th IEEE-RAS Intl Conf on Humanoid Robots}, pdf = {http://autonomous-learning.org/wp-content/uploads/haschke1.pdf} } - J. J. Alcaraz-Jiménez, M. Missura, and H. M. S. Behnke: Lateral disturbance rejection for the nao robot. In In proceedings of 16th robocup international symposium, Springer, Best Paper Award, 2012. [Bibtex]
@InProceedings{ LateralControlNao, author = {Juan José Alcaraz-Jiménez and Marcell Missura and Humberto Martínez-Barberáand Sven Behnke}, title = {Lateral Disturbance Rejection for the Nao Robot}, booktitle = {In Proceedings of 16th RoboCup International Symposium}, year = {2012}, publisher = {Springer}, note = {Best Paper Award}, pdf = {http://autonomous-learning.org/wp-content/uploads/Lateral_Disturbance_Rejection.pdf} } - A. Krueger, O. Walter, V. Leutnant, and R. Haeb-Umbach: Bayesian feature enhancement for asr of noisy reverberant real-worlddata. In Proceedings of interspeech, 2012. [Bibtex]
@InProceedings{ KruegerWalterLeutnantHaebUmbach, author = { A. Krueger and O. Walter and V. Leutnant and R. Haeb-Umbach}, title = {Bayesian Feature Enhancement for ASR of Noisy Reverberant Real-WorldData}, booktitle = {Proceedings of INTERSPEECH}, year = {2012}, pdf = {http://autonomous-learning.org/wp-content/uploads/WalterHaeb-Umbach_Interspeech2012-1.pdf} } - S. Kazerounian, M. Luciw, M. Richter, and Y. Sandamirskaya: Autonomous reinforcement of behavioral sequences in neural dynamics. In Proceedings of the joint ieee international conference on development and learning & epigenetic robotics (icdl-epirob), 2012. [Bibtex]
@InProceedings{ KazerounianEtAl2012, author = {Kazerounian, S. and Luciw, M and Richter, M. and Sandamirskaya, Y.}, title = {Autonomous Reinforcement of Behavioral Sequences in Neural Dynamics}, booktitle = {Proceedings of the Joint IEEE International Conference on Development and Learning \& Epigenetic Robotics (ICDL-EPIROB)}, year = {2012}, pdf = {http://arxiv.org/pdf/1210.3569.pdf} } - J. Fürnkranz and E. Hüllermeier: Preference learning. In Encyclopedia of the sciences of learning, 986, Springer-Verlag, 2012. [Bibtex]
@InCollection{ jf:PreferenceLearning-EncLearningSciences, author = {F{\"{u}}rnkranz, Johannes and H{\"{u}}llermeier, Eyke}, editor = {Seel, Norbert M.}, title = {Preference Learning}, booktitle = {Encyclopedia of the Sciences of Learning}, year = {2012}, pages = {986}, publisher = {Springer-Verlag} } - J. Fürnkranz, E. Hüllermeier, W. Cheng, and S. Park: Preference-based reinforcement learning: a formal framework and a policy iteration algorithm. Machine learning, 89, 123-156, Special Issue of Selected Papers from ECML PKDD 2011, 2012. [Bibtex]
@Article{ jf:MLJ-PrefBasedRL, author = {F{\"{u}}rnkranz, Johannes and H{\"{u}}llermeier, Eyke and Cheng, Weiwei and Park, Sang-Hyeun}, keywords = {Preference learning, Reinforcement learning}, title = {Preference-based Reinforcement Learning: A Formal Framework and a Policy Iteration Algorithm}, journal = {Machine Learning}, volume = {89}, number = {1-2}, year = {2012}, pages = {123--156}, note = {Special Issue of Selected Papers from ECML PKDD 2011}, issn = {0885-6125}, doi = {10.1007/s10994-012-5313-8}, abstract = {This paper makes a first step toward the integration of two subfields of machine learning, namely preference learning and reinforcement learning (RL). An important motivation for a preference-based approach to reinforcement learning is the observation that in many real-world domains, numerical feedback signals are not readily available, or are defined arbitrarily in order to satisfy the needs of conventional RL algorithms. Instead, we propose an alternative framework for reinforcement learning, in which qualitative reward signals can be directly used by the learner. The framework may be viewed as a generalization of the conventional RL framework in which only a partial order between policies is required instead of the total order induced by their respective expected long-term reward. Therefore, building on novel methods for preference learning, our general goal is to equip the RL agent with qualitative policy models, such as ranking functions that allow for sorting its available actions from most to least promising, as well as algorithms for learning such models from qualitative feedback. As a proof of concept, we realize a first simple instantiation of this framework that defines preferences based on utilities observed for trajectories. To that end, we build on an existing method for approximate policy iteration based on roll-outs. While this approach is based on the use of classification methods for generalization and policy learning, we make use of a specific type of preference learning method called label ranking. Advantages of preference-based approximate policy iteration are illustrated by means of two case studies.} } - G. Büscher, R. Kõiva, Carsten Schürmann, R. Haschke, and H. J. Ritter: Tactile dataglove with fabric-based sensors. In Ieee-ras international conference on humanoid robots (humanoids 2012), 2012. [Bibtex]
@Conference{ HaschkeRitterb, author = {Gereon B{\"u}scher and Risto K{\~o}iva and Carsten Sch{\"u}rmann and Robert Haschke and Helge J. Ritter}, title = {Tactile dataglove with fabric-based sensors}, booktitle = {IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012)}, year = {2012}, address = {Osaka, Japan}, month = {29/11/2012} } - G. Büscher, R. Kõiva, Carsten Schürmann, R. Haschke, and H. Ritter: Flexible and stretchable fabric-based tactile sensor. In Ieee/rsj international conference on intelligent robots and systems (iros 2012) workshop on advances in tactile sensing and touch based human-robot interaction, 2012. [Bibtex]
@Conference{ HaschkeRittera, author = {Gereon B{\"u}scher and Risto K{\~o}iva and Carsten Sch{\"u}rmann and Robert Haschke and Helge Ritter}, title = {Flexible and stretchable fabric-based tactile sensor}, booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2012) Workshop on Advances in Tactile Sensing and Touch based Human-Robot Interaction}, year = {2012}, address = {Vilamoura, Algarve, Portugal}, month = {11/10/2012}, pdf = {http://autonomous-learning.org/wp-content/uploads/haschke3.pdf} } - B. Duran, Y. Sandamirskaya, and G. Schöner: A dynamic field architecture for the generation of hierarchically organized sequences. In Artificial neural networks and machine learning – icann 2012, 7552, 25-32, Springer Berlin Heidelberg, 2012. [Bibtex]
@InCollection{ DuranSandamirskayaSchoner2012, author = {Duran, Boris and Sandamirskaya, Yulia and Sch{\"o}ner, Gregor}, title = {A Dynamic Field Architecture for the Generation of Hierarchically Organized Sequences}, booktitle = {Artificial Neural Networks and Machine Learning – ICANN 2012}, publisher = {Springer Berlin Heidelberg}, year = {2012}, editor = {Villa, AlessandroE.P. and Duch, Włodzisław and Érdi, Péter and Masulli, Francesco and Palm, Günther}, volume = {7552}, series = {Lecture Notes in Computer Science}, pages = {25-32}, pdf = {http://dx.doi.org/10.1007/978-3-642-33269-2_4} } - B. Duran and Y. Sandamirskaya: Neural dynamics of hierarchically organized sequences: a robotic implementation. In The ieee-ras international conference on humanoid robots (humanoids), 2012. [Bibtex]
@Conference{ DuranSandamirskaya2012, author = {Duran, B and Sandamirskaya, Y}, title = {Neural Dynamics of Hierarchically Organized Sequences: a Robotic Implementation}, booktitle = {The IEEE-RAS International Conference on Humanoid Robots (Humanoids)}, year = {2012} } - W. Böhmer, S. Grünewälder, H. Nickisch, and K. Obermayer: Generating feature spaces for linear algorithms with regularized sparse kernel slow feature analysis. Machine learning, 89, 67-86, 2012. [Bibtex]
@Article{ boehmer_2012, title = {Generating feature spaces for linear algorithms with regularized sparse kernel slow feature analysis}, author = {Böhmer, W. and Grünewälder, S. and Nickisch, H. and Obermayer, K.}, pages = {67--86}, year = {2012}, journal = {Machine Learning}, volume = {89}, number = {1}, abstract = {Without non-linear basis functions many problems can not be solved by linear algorithms. This article proposes a method to automatically construct such basis functions with slow feature analysis (SFA). Non-linear optimization of this unsupervised learning method generates an orthogonal basis on the unknown latent space for a given time series. In contrast to methods like PCA, SFA is thus well suited for techniques that make direct use of the latent space. Real-world time series can be complex, and current SFA algorithms are either not powerful enough or tend to over-fit. We make use of the kernel trick in combination with sparsification to develop a kernelized SFA algorithm which provides a powerful function class for large data sets. Sparsity is achieved by a novel matching pursuit approach that can be applied to other tasks as well. For small data sets, however, the kernel SFA approach leads to over-fitting and numerical instabilities. To enforce a stable solution, we introduce regularization to the SFA objective. We hypothesize that our algorithm generates a feature space that resembles a Fourier basis in the unknown space of latent variables underlying a given real-world time series. We evaluate this hypothesis at the example of a vowel classification task in comparison to sparse kernel PCA. Our results show excellent classification accuracy and demonstrate the superiority of kernel SFA over kernel PCA in encoding latent variables.}, pdf = {http://www.ni.tu-berlin.de/fileadmin/fg215/articles/Generating_feature_spaces.pdf} } - M. Lopes, T. Lang, and M. Toussaint: Exploration in model-based reinforcement learning by empirically estimating learning progress. In Neural information processing systems (nips 2012), 2012. [Bibtex]
@InProceedings{ 12-lopes-NIPS, key = "NIPS", author = "Manuel Lopes and Tobias Lang and Marc Toussaint", title = "Exploration in Model-based Reinforcement Learning by Empirically Estimating Learning Progress", booktitle = "Neural Information Processing Systems (NIPS 2012)", year = "2012", url = {http://ipvs.informatik.uni-stuttgart.de/mlr/marc/publications/12-lopes-NIPS.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/12-lopes-NIPS.pdf} } - T. Lang, M. Toussaint, and K. Kersting: Exploration in relational domains for model-based reinforcement learning. Journal of machine learning research, 13, 3691-3734, 2012. [Bibtex]
@Article{ 12-lang-JMLR, key = "JMLR", title = "Exploration in Relational Domains for Model-based Reinforcement Learning", author = "Tobias Lang and Marc Toussaint and Kristian Kersting", journal = "Journal of Machine Learning Research", year = "2012", volume = "13", pages = "3691-3734", url = {https://ipvs.informatik.uni-stuttgart.de/mlr/marc/publications/12-lang-JMLR.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/12-lang-JMLR.pdf} } - A. Kumar, S. Zilberstein, and M. Toussaint: Message passing algorithms for map estimation using dc programming. In Int. conf. on artificial intelligence and statistics (aistats 2012), 656-664, 2012. [Bibtex]
@InProceedings{ 12-kumar-AISTATS, key = "AISTATS", author = "Akshat Kumar and Shlomo Zilberstein and Marc Toussaint", year = "2012", title = "Message Passing Algorithms for MAP Estimation Using DC Programming", booktitle = "Int.{} Conf.{} on Artificial Intelligence and Statistics (AISTATS 2012)", pages = "656-664", url = {http://ipvs.informatik.uni-stuttgart.de/mlr/marc/publications/12-kumar-AISTATS.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/12-kumar-AISTATS.pdf} } - M. Botvinick and M. Toussaint: Planning as probabilistic inference. Trends in cognitive sciences, 16, 485-488, 2012. [Bibtex]
@Article{ 12-botvinick-TICS, key = "TICS", author = "Matthew Botvinick and Marc Toussaint", title = "Planning as probabilistic inference", journal = "Trends in Cognitive Sciences", volume = "16", pages = "485-488", year = "2012", url = {http://ipvs.informatik.uni-stuttgart.de/mlr/marc/publications/12-botvinick-TICS.pdf}, pdf = {https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/12-botvinick-TICS.pdf} }
2011
- W. Samek, M. Kawanabe, and C. Vidaurre: Group-wise stationary subspace analysis – a novel method for studying non-stationarities. In Proc. 5th int. bci conf. graz, 16-20, Verlag der Technischen Universität Graz, 2011. [Bibtex]
@InCollection{ SamKawVid11, author = {Samek, Wojciech and Kawanabe, Motoaki and Vidaurre, Carmen}, title = {Group-wise Stationary Subspace Analysis - A novel method for studying non-stationarities}, booktitle = {Proc. 5th Int. BCI Conf. Graz}, publisher = {Verlag der Technischen Universit{\"a}t Graz}, year = {2011}, editor = {M{\"u}ller-Putz, G. R. and Scherer, R. and Billinger, M. and Kreilinger, A. and Kaiser, V. and Neuper, C.}, pages = {16-20}, address = {Graz}, folder = {BBCI}, isbn = {978-3-85125-140-1}, pdf = {http://autonomous-learning.org/wp-content/uploads/SamBCI11.pdf} }
2010
- C. Sannelli, C. Vidaurre, K. Müller, and B. Blankertz: Common spatial pattern patches – an optimized filter ensemble for adaptive brain-computer interfaces. In Conf proc ieee eng med biol soc, 2010, 4351-4354, 2010. [Bibtex]
@InProceedings{ SanVidMueBla10, author = {Sannelli, Claudia and Vidaurre, Carmen and M\"uller, Klaus-Robert and Blankertz, Benjamin}, title = {Common Spatial Pattern Patches - an Optimized Filter Ensemble for Adaptive Brain-Computer Interfaces}, booktitle = {Conf Proc IEEE Eng Med Biol Soc}, year = {2010}, volume = {2010}, pages = {4351--4354}, file = {SanVidMueBla10.pdf:http\://doc.ml.tu-berlin.de/bbci/publications/SanVidMueBla10.pdf:PDF}, folder = {BBCI}, grants = {Vital-BCI,BFNT,brain@work,TOBI,Pascal2}, pdf = {http://dx.doi.org/10.1109/IEMBS.2010.5626227} }