This is an archived version of the Machine Learning Lab website for documentation purposes. The host is in no way affiliated with the University of Freiburg, its Faculty of Engineering or any of its members.

This list contains only publications involving current members of the Machine Learning Lab. For a comprehensive list of all publications involving former chair Prof. Dr. Martin Riedmiller, please see his list of publications.

Publications

2016

  • SS Kumar, J Wülfing, S Okujeni, J Boedecker, M Riedmiller, U Egert (2016) Autonomous Optimization of Targeted Stimulation of Neuronal Networks. PLoS Comput Biol 12 (8) pp. e1005054. web Bibtex
  • Jost Tobias Springenberg (2016) Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks. In International Conference on Learning Representations (ICLR). web Bibtex
  • J. T. Springenberg, A. Klein, S. Falkner, F. Hutter (2016) Bayesian Optimization with Robust Bayesian Neural Networks. In Advances in Neural Information Processing Systems 29. Bibtex

2015

  • M. Feurer, T. Springenberg, F. Hutter (2015) Initializing Bayesian Hyperparameter Optimization via Meta-Learning. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence. web Bibtex
  • T. Domhan, J. T. Springenberg, F. Hutter (2015) Speeding up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves. In Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI). web Bibtex
  • Wendelin Böhmer, Jost Tobias Springenberg, Joschka Boedecker, Martin Riedmiller, Klaus Obermayer (2015) 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 pp. 1-10. Springer Berlin Heidelberg. doi web Bibtex
  • A.Dosovitskiy, J.T.Springenberg, T.Brox (2015) Learning to Generate Chairs with Convolutional Neural Networks. In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR). web Bibtex
  • J. T. Springenberg, A. Dosovitskiy, T. Brox, M. Riedmiller (2015) Striving for Simplicity: The All Convolutional Net. In arXiv:1412.6806, also appeared at ICLR 2015 Workshop Track. web Bibtex
  • Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Tobias Springenberg, Manuel Blum, Frank Hutter (2015) Efficient and Robust Automated Machine Learning. In Advances in Neural Information Processing Systems. PDF Bibtex
  • A. Eitel, J. T. Springenberg, L. Spinello, M. Riedmiller, W. Burgard (2015) Multimodal Deep Learning for Robust RGB-D Object Recognition. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). web Bibtex
  • Manuel Watter, Jost Springenberg, Joschka Boedecker, Martin Riedmiller (2015) Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images. In Advances in Neural Information Processing Systems 28. pp. 2728–2736. PDF Bibtex

2014

  • Thomas Lampe, Martin Riedmiller (2014) Approximate Model-Assisted Neural Fitted Q-Iteration. In IEEE International Joint Conference on Neural Networks (IJCNN 2014). Beijing, China. PDF Bibtex
  • Oliver Obst, Joschka Boedecker (2014) Guided Self-Organization of Input-Driven Recurrent Neural Networks. In Guided Self-Organization: Inception. pp. 319-340. Springer Berlin Heidelberg. doi web Bibtex
  • Thomas Lampe, Lukas D. J. Fiederer, Martin Voelker, Alexander Knorr, Martin Riedmiller, Tonio Ball (2014) A Brain-Computer Interface for High-Level Remote Control of an Autonomous, Reinforcement-Learning-Based Robotic System for Reaching and Grasping. In International Conference on Intelligent User Interfaces (IUI 2014). Haifa, Israel. web Bibtex
  • Tobias Domhan, Jost Tobias Springenberg, Frank Hutter (2014) Extrapolating Learning Curves of Deep Neural Networks. In ICML 2014 AutoML Workshop. web Bibtex
  • Matthias Feurer, Jost Tobias Springenberg, Frank Hutter (2014) Using Meta-Learning to Initialize Bayesian Optimization of Hyperparameters. In ECAI workshop on Metalearning and Algorithm Selection (MetaSel). web Bibtex
  • Alexey Dosovitskiy, Jost Tobias Springenberg, Martin Riedmiller, Thomas Brox (2014) Discriminative Unsupervised Feature Learning with Convolutional Neural Networks. In 28th Annual Conference on Neural Information Processing Systems (NIPS). Bibtex
  • Joschka Boedecker, Jost Tobias Springenberg, Jan Wülfing, Martin Riedmiller (2014) Approximate Real-Time Optimal Control Based on Sparse Gaussian Process Models. In Adaptive Dynamic Programming and Reinforcement Learning (ADPRL). PDF Bibtex
  • M Duempelmann, S Ewing, M Blum, R Rostek, P Woias, M Riedmiller, A Schulze-Bonhage (2014) Investigation of low complexity seizure detection algorithm for closed loop devices in epilepsy treatment. Clinical Neurophysiology pp. S80. Bibtex

2013

  • Manuel Blum, Martin Riedmiller (2013) Optimization of Gaussian Process Hyperparameters using Rprop. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. PDF Bibtex
  • Manuel Blum, Martin Riedmiller (2013) Electricity Demand Forecasting using Gaussian Processes. In The AAAI-13 Workshop on Trading Agent Design and Analysis (TADA-13). PDF Bibtex
  • Thomas Lampe, Martin Riedmiller (2013) Acquiring Visual Servoing Reaching and Grasping Skills using Neural Reinforcement Learning. In IEEE International Joint Conference on Neural Networks (IJCNN 2013). Dallas, TX. PDF Bibtex
  • Joschka Boedecker, Thomas Lampe, Martin Riedmiller (2013) Modeling effects of intrinsic and extrinsic rewards on the competition between striatal learning systems. Frontiers in Psychology 4 (739) doi web Bibtex
  • Alexey Dosovitskiy, Jost Tobias Springenberg, Thomas Brox (2013) Unsupervised feature learning by augmenting single images . In arXiv:1312.5242, also appeared at ICLR 2014 Workshop Track. web Bibtex
  • Jost Tobias Springenberg, Martin Riedmiller (2013) Improving Deep Neural Networks with Probabilistic Maxout Units. In arXiv:1312.6116, also appeared at ICLR 2014 Workshop Track. web Bibtex
  • Oliver Obst, Joschka Boedecker, Benedikt Schmidt, Minoru Asada (2013) On active information storage in input-driven systems. arXiv.org. web Bibtex

2012

  • Oliver Obst, Joschka Boedecker, Benedikt Schmidt, Minoru Asada (September 2012) Computing local active information storage in input-driven systems. Bibtex
  • Christoph Hartmann AND Joschka Boedecker AND Oliver Obst AND Shuhei Ikemoto AND Minoru Asada (July 2012) Real-Time Inverse Dynamics Learning for Musculoskeletal Robots based on Echo State Gaussian Process Regression. In Proceedings of Robotics: Science and Systems. Sydney, Australia. Bibtex
  • Joschka Boedecker, Oliver Obst, Yuki Kashima, Minoru Asada (March 29-30 2012) Intrinsic computational capabilities of reservoir computing networks in different dynamics regimes and their relation to task performance. Lyon, France. Bibtex
  • Manuel Blum, Jost Tobias Springenberg, Jan Wülfing, Martin Riedmiller (2012) A Learned Feature Descriptor for Object Recognition in RGB-D Data. In IEEE International Conference on Robotics and Automation (ICRA). St. Paul, Minnesota, USA. PDF Bibtex
  • Jost Tobias Springenberg, Martin Riedmiller (2012) Learning temporal coherent features through life-time sparsity. In International Conference on Neural Information Processing (ICONIP). pp. 347–356. Bibtex
  • Joschka Boedecker, Oliver Obst, Joseph T Lizier, N Michael Mayer, Minoru Asada (2012) Information processing in echo state networks at the edge of chaos.. Theory in Biosciences 131 (3) pp. 205–213. Springer Berlin / Heidelberg. doi web Bibtex

2011

  • Beata J. Grzyb, Joschka Boedecker, Minoru Asada, Angel P. del Pobil (September 2011) Elevated activation of dopaminergic brain areas facilitates behavioral state transition. In IROS 2011 Workshop on Cognitive Neuroscience Robotics. Bibtex
  • Joschka Boedecker, Minoru Asada (2011) Towards Self-organized Online Extraction of Invariances Using a Hierarchy of Multiple-timescale Reservoirs. Bibtex
  • Manuel Blum, Jost Tobias Springenberg, Jan Wülfing, Martin Riedmiller (2011) On the Applicability of Unsupervised Feature Learning for Object Recognition in RGB-D Data. In NIPS Workshop on Deep Learning and Unsupervised Feature Learning. Granada, Spain. PDF Bibtex
  • Beata J. Grzyb, Joschka Boedecker, Minoru Asada, Angel P. del Pobil, Linda B. Smith (2011) Between Frustration and Elation: Sense of Control Regulates the Intrinsic Motivation for Motor Learning. Bibtex
  • Beata J. Grzyb, Joschka Boedecker, Minoru Asada, Angel P. del Pobil, Linda B. Smith (2011) Trying anyways: how ignoring the errors may help in learning new skills. In First Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Bibtex
  • Joschka Boedecker (2011) Echo State Network Reservoir Shaping and Information Dynamics at the Edge of Chaos. Osaka, Japan. Bibtex
  • Tim Landgraf, Anselm Brachmann, Manuel Blum, Ra{ú}l Rojas (2011) Unsupervised Neural Coding of Nightingale Songs Using Deep Autoencoders. In Computational Neuroscience & Neurotechnology Bernstein Conference & Neurex Annual Meeting. Bibtex
  • Manuel Blum, Martin Riedmiller (2011) Q-function Approximation in Batch Mode Reinforcement Learning. In International Workshop on Bio-Inspired Robots. Bibtex

2010

  • Oliver Obst, Joschka Boedecker, Minoru Asada (2010) Improving Recurrent Neural Network Performance Using Transfer Entropy. In Neural Information Processing Models and Applications. pp. 193–200. Springer. web Bibtex

2009

  • Joschka Boedecker, Oliver Obst, Norbert Michael Mayer, Minoru Asada (Oct 2009) Initialization and Self-Organized Optimization of Recurrent Neural Network Connectivity. HFSP Journal 3 (5) pp. 340–349. doi web Bibtex
  • Joschka Boedecker, Oliver Obst, Norbert Michael Mayer, Minoru Asada (apr 2009) Studies on Reservoir Initialization and Dynamics Shaping in Echo State Networks. In Proceedings of the 17th European Symposium On Artificial Neural Networks ({ESANN}'09). pp. 227–232. D-Side Publications. Evere, Belgium. web Bibtex
  • Norbert Michael Mayer, Joschka Boedecker, Minoru Asada (2009) Robot motion description and real-time management with the Harmonic Motion Description Protocol. Robotics and Autonomous Systems 57 (8) pp. 870-876. web Bibtex

2008

  • Rodrigo da Silva Guerra, Joschka Boedecker, Norbert Michael Mayer, Shinzo Yanagimachi, Yasuji Hirosawa, Kazuhiko Yoshikawa, Masaaki Namekawa, Minoru Asada (2008) Introducing Physical Visualization Sub-League. In RoboCup 2007: Robot Soccer World Cup XI. pp. 496–503. Springer. Bibtex
  • Norbert Michael Mayer, Joschka Boedecker, Kazuhiro Masui, Masaki Ogino, Minoru Asada (2008) HMDP: A new protocol for motion pattern generation towards behavior abstraction. In RoboCup 2007: Robot Soccer World Cup XI. pp. 184-195. Springer. web Bibtex
  • Joschka Boedecker, Minoru Asada (2008) SimSpark – Concepts and Application in the 3D Soccer Simulation League. In Workshop on The Universe of RoboCup Simulators at SIMPAR 2008. web Bibtex

2007

  • Norbert Michael Mayer, Joschka Boedecker, Rodrigo da Silva Guerra, Minoru Asada (2007) 3D2Real: Simulation League Finals in Real Robots. In RoboCup 2006: Robot Soccer World Cup X. pp. 25-34. web Bibtex
  • Rodrigo da Silva Guerra, Joschka Boedecker, Minoru Asada (2007) Physical Visualization Sub-League: A New Platform for Research and Edutainment. pp. 15–20. Bibtex
  • Rodrigo da Silva Guerra, Joschka Boedecker, Shinzo Yanagimachi, Minoru Asada (2007) Introducing a New Minirobotics Platform for Research and Edutainment. In Proceedings of the 4th International Symposium on Autonomous Minirobots for Research and Edutainment. Bibtex
  • Rodrigo da Silva Guerra, Joschka Boedecker, Norbert Michael Mayer, Shinzo Yanagimachi, Hiroshi Ishiguro, Minoru Asada (2007) A new minirobotics system for teaching and researching agent-based programming. In CATE '07: Proceedings of the 10th IASTED International Conference on Computers and Advanced Technology in Education. pp. 39–44. ACTA Press. Anaheim, CA, USA. Bibtex
  • Michael Mayer, Joschka Boedecker, Minoru Asada (2007) On Standardization in the RoboCup Soccer Humanoids Leagues. web Bibtex

2006

  • Minoru Asada, Norbert Michael Mayer, Joschka Boedecker, Masaki Ogino, Sawa Fuke (2006) The RoboCup Soccer Humanoid League: Overview and Outlook. web Bibtex
  • Oliver Obst, Joschka Boedecker (2006) Flexible Coordination of Multiagent Team Behavior using HTN Planning. In RoboCup 2005: Robot Soccer World Cup IX. pp. 521-528. Springer. web Bibtex
  • Joschka Boedecker, Norbert Michael Mayer, Masaki Ogino, Rodrigo da Silva Guerra, Masaki Kikuchi, Minoru Asada (2006) Getting closer: How Simulation and Humanoid League can benefit from each other. In Proceedings of the 3rd International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE 2005). pp. 93-98. Springer. web Bibtex

2005

  • Oliver Obst, Anita Maas, Joschka Boedecker (Jul 2005) HTN Planning for Flexible Coordination Of Multiagent Team Behavior. pp. 87–94. Edinburgh, Scotland. Bibtex
  • Joschka Boedecker, Norbert Michael Mayer, Masaki Ogino, Rodrigo da Silva Guerra, Masaaki Kikuchi, Minoru Asada (2005) Getting closer: How Simulation and Humanoid League can benefit from each other. Universität Koblenz-Landau. Universität Koblenz-Landau, Institut für Informatik, Universitätsstr. 1, D-56070 Koblenz. web Bibtex
  • Oliver Obst, Anita Maas, Joschka Boedecker (2005) HTN Planning for Flexible Coordination Of Multiagent Team Behavior. Universität Koblenz-Landau. Universität Koblenz-Landau, Institut für Informatik, Universitätsstr. 1, D-56070 Koblenz. web Bibtex