- MASCHINELLES LERNEN UND BIO-INSPIRIERTE OPTIMIERUNG
- I. Lovrek, R.J. Howlett, and L.C. Jain (Eds.): KES 2008, Part I, LNAI 5177, p. 11, 2008. Springer-Verlag Berlin Heidelberg 2008
- Accelerated Learning in BackPropagation Nets In R. Pfeifer, Z. Schreter, Z. Fogelman, and L. Steels, editors, Connectionism in Perspective, pages
- Active Learning with Adaptive Grids Michele Milano 1 , Jurgen Schmidhuber 2 , and Petros Koumoutsakos 1?
- EVALUATING LONGTERM DEPENDENCY BENCHMARK PROBLEMS BY RANDOM GUESSING
- LEARNING COMPLEX, EXTENDED SEQUENCES USING THE PRINCIPLE OF HISTORY COMPRESSION
- A PositiveEvidence Model for Rhythmical Beat Induction # Douglas Eck
- Policy Gradients with Parameter-Based Exploration for Control
- The New AI: General & Sound & Relevant for Jurgen Schmidhuber
- International Journal of Foundations of Computer Science Vol 13 No. 4 (2002) 587-612 World Scienti c Publishing Company. Based on http://arXiv.org/abs/quant-ph/0011122, 2000
- A First Look at Music Composition using LSTM Recurrent Neural Networks
- Technical Report IDSIA-05-04 A Coding Theorem for
- J. Schmidhuber. The Speed Prior: A new simplicity measure yielding near-optimal computable predictions. In J. Kivinen and R. H. Sloan, editors, Proceed-
- Frontier Search Sun Yi, Tobias Glasmachers, Tom Schaul, and Jurgen Schmidhuber
- FACIAL BEAUTY AND FRACTAL GEOMETRY Note IDSIA2898, June 16, 1998
- REALISTIC MULTIAGENT REINFORCEMENT LEARNING
- In J. A. Meyer and S. W. Wilson, editors, Proc. of the International Conference on Simulation of Adaptive Be
- Discovering Solutions with Low Kolmogorov Complexity and High Generalization Capability
- Siemens AG, CT IC 4, H.-G. Zimmermann1 CORPORATETECHNOLOGY
- Machine Learning, 54, 211254, 2004 c 2004 Kluwer Academic Publishers. Manufactured in The Netherlands.
- CURIOUS MODELBUILDING CONTROL SYSTEMS In Proc. International Joint Conference on Neural Networks, Singapore, volume 2, pages 14581463. IEEE, 1991.
- Solving POMDPs with Levin Search and EIRA In Machine Learning: Proceedings of the 13th international conference, 1996
- LEARNING TEMPORARY VARIABLE BINDING WITH DYNAMIC LINKS
- Framewise Phoneme Classification with Bidirectional LSTM and Other Neural Network
- Super Mario Evolution Julian Togelius, Sergey Karakovskiy, Jan Koutnik and Jurgen Schmidhuber
- arXiv:0812.4360v2[cs.AI]15Apr2009 Driven by Compression Progress
- Reinforcement Learning in Partially Observable Mobile Robot Domains Using Unsupervised Event Extraction
- Long Short-Term Memory Learns Context Free and Context Sensitive Languages
- HPIPE: Facilitating Hierarchical Program Evolution through Skip Nodes
- Source Separation as a ByProduct of Regularization \Lambda
- In Proceedings of the International Conference on Intelligent Robotics and Systems (IROS 2006) A System for Robotic Heart Surgery that Learns to
- Godel Machines: Fully Self-referential Optimal Universal Self-improvers
- arXiv:cs.NE/0512062v115Dec2005 Evolino for Recurrent Support Vector Machines
- Efficient Natural Evolution Strategies Manno 6928, Switzerland
- Learning to Forget: Continual Prediction with LSTM Felix A. Gers Jurgen Schmidhuber Fred Cummins
- Manuscript Number: 1990 Learning to Forget: Continual
- A Fast, Compact Approximation of the Exponential Function
- Evolving Structured Programs with Hierarchical Instructions and Skip Nodes
- Reinforcement Learning with Interacting Continually Running Fully Recurrent Networks
- LEARNING TO GENERATE SUBGOALS FOR ACTION SEQUENCES (To appear in O. Simula, editor, Proceedings of the International Conference
- A FIXED SIZE STORAGE O(n 3 ) TIME COMPLEXITY LEARNING ALGORITHM
- Journal of Autonomous Robots, , 1--12 (1999) fl 1999 Kluwer Academic Publishers, Boston. Manufactured in The Netherlands.
- Training Recurrent Networks by Evolino Jurgen Schmidhuber
- Formal Theory of Creativity, Fun, and Intrinsic Motivation (1990-2010)
- Parameter-exploring Policy Gradients Frank Sehnkea
- Ultimate Cognition a` la Godel Jurgen Schmidhuber
- Simple Algorithmic Theory of Subjective Beauty, Novelty, Surprise, Interestingness, Attention,
- arXiv:0812.4360v1[cs.AI]23Dec2008 Driven by Compression Progress
- Journal of Machine Learning Research 9 (2008) 937-965 Submitted 8/07; Revised 2/08; Published 5/08 Accelerated Neural Evolution through
- Developmental Robotics, Optimal Artificial Curiosity,
- IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. XX, NO. Y, MONTH 2002 1 Self-Organizing Nets for Optimization
- Network: Comput. Neural Syst. 10 (1999) 133169. Printed in the UK PII: S0954-898X(99)95514-8 Processing images by semi-linear predictability minimization
- Five Answers on Randomness Jurgen Schmidhuber
- Art & Science as By-Products of Search for Novel Patterns, or Data Compressible in
- Exponential Natural Evolution Strategies Tobias Glasmachers
- Artificial Scientists & Artists Based on the Formal Theory of Creativity Jurgen Schmidhuber
- Evolving memory cell structures for sequence learning
- An EM based training algorithm for recurrent neural networks
- Scalable Neural Networks for Board Games Tom Schaul and Jurgen Schmidhuber
- Hierarchical Controller Learning in a First-Person Shooter Niels van Hoorn, Julian Togelius and Jurgen Schmidhuber
- A Scalable Neural Network Architecture for Board Games Tom Schaul, Jurgen Schmidhuber
- Episodic Reinforcement Learning by Logistic Reward-Weighted Regression
- Natural Evolution Strategies Daan Wierstra, Tom Schaul, Jan Peters and Juergen Schmidhuber
- Learning What to Ignore: Memetic Climbing in Topology and Weight space
- Policy Gradient Critics Daan Wierstra1
- A Novel Approach to On-Line Handwriting Recognition Based on Bidirectional Long Short-Term Memory Networks
- An application of recurrent neural networks to discriminative keyword spotting
- Multi-Dimensional Recurrent Neural Networks Alex Graves1
- Solving Deep Memory POMDPs with Recurrent Policy Gradients
- Sequence Labelling in Structured Domains with Hierarchical Recurrent Neural Networks
- Prefix-like Complexities of Finite and Infinite Sequences on Generalized Turing Machines
- Dynamic Algorithm Portfolios Matteo Gagliolo
- Completely Self-referential Optimal Reinforcement Learners
- A Robot that Reinforcement-Learns to Identify and Memorize Important Previous Observations
- Steering committee and administration staff: (left to right) Enza (admin), Eve, Frank, Mario, Erik, Tiziana (admin) and Grard.
- Long ShortLong Short--Term Memory:Term Memory: 20032003 Tutorial on LSTM Recurrent NetsTutorial on LSTM Recurrent Nets
- Probabilistic and Bayesian Analytics
- Hidden Markov Following a lecture by Andrew W. Moore
- April 23rd, 2002Copyright 2002, Andrew W. Moore Andrew W. Moore
- Advanced Robotics 22 (2008) 3955 www.brill.nl/ar
- Evolution of National Nobel Prize Shares in the 20th Century Jurgen Schmidhuber
- arXiv:quant-ph/0011122v220Dec2000 Technical Report IDSIA-20-00, Version 2.0; 20 Dec 2000
- Neural Processing of Complex Continual Input Streams Felix A. Gers Jurgen Schmidhuber
- MODELBASED REINFORCEMENT LEARNING FOR EVOLVING SOCCER
- Fast Curvature Matrix-Vector Products for Second-Order Gradient Descent
- Technical Report IDSIA1599 Online Independent Component Analysis
- Direct Policy Computation by the Liouville Machine Ivo Kwee and Jurgen Schmidhuber
- Finding Downbeats with a Relaxation Oscillator # Douglas Eck
- Market-Based Reinforcement Learning in Partially Observable Worlds
- INCREMENTAL SELFIMPROVEMENT FOR LIFETIME MULTIAGENT REINFORCEMENT LEARNING
- HQLearning Adaptive Behavior 6:2, 1997 (in press)
- Reinforcement Learning with Long ShortTerm Memory
- The New AI: General & Sound & Relevant for Physics
- WHAT'S INTERESTING? Technical Report IDSIA3597, Version 1.0
- Bias-Optimal Incremental Problem Solving Jurgen Schmidhuber
- GRUNDLAGEN ALGORITHMISCHER INFORMATIONSTHEORIE
- arXiv:cs.AI/0207097v131Jul2002 Technical Report IDSIA-12-02, Version 1.0; 31 July 2002
- State-Dependent Exploration for Policy Gradient Methods
- Networks Adjusting Networks Technical Report FKI12990, 1990
- REDUCING THE RATIO BETWEEN LEARNING COM PLEXITY AND NUMBER OF TIME VARYING VARIABLES
- A `SELFREFERENTIAL' WEIGHT MATRIX J. Schmidhuber
- Evolving strategies for active flow control Michele Milano
- Evolving Modular Fast-Weight Networks for Control
- Hierarchical Reinforcement Learning Based on Subgoal Discovery and Subpolicy Specialization
- Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition
- Unsupervised Learning in LSTM Recurrent Neural Networks
- Machine Learning, 28, 105--132 (1997) fl 1997 Kluwer Academic Publishers, Boston. Manufactured in The Netherlands.
- ADAPTIVE HISTORY COMPRESSION FOR LEARNING TO DIVIDE AND CONQUER
- A Local Learning Algorithm for Dynamic Feedforward and Recurrent Networks
- Learning to Predict Through Probabilistic Incremental Program Evolution and Automatic Task Decomposition
- A GENERAL METHOD FOR INCREMENTAL SELFIMPROVEMENT
- CMAC Models Learn to Play Soccer To appear in the 8th International Conference on Artificial Neural Networks
- SEMILINEAR PREDICTABILITY MINIMIZATION PRODUCES WELLKNOWN FEATURE DETECTORS
- Improving Long-Term Online Prediction with Decoupled Extended Kalman Filters ?
- Recurrent Nets that Time and Count Felix A. Gers Jurgen Schmidhuber
- An OnLine Algorithm for Dynamic Reinforcement Learning and Planning in Reactive Environments
- LEARNING UNAMBIGUOUS REDUCED SEQUENCE DESCRIPTIONS
- Machine Learning, , --(1998, in press) fl 1998 Kluwer Academic Publishers, Boston. Manufactured in The Netherlands.
- CONTINUOUS HISTORY COMPRESSION In H. Huning, S. Neuhauser, M. Raus, and W. Ritschel, editors, Proc. of Intl. Workshop on Neural
- In J. A. Meyer, H. L. Roitblat, and S. W. Wilson, editors, Proc. of the 2nd International Conference on Simulation of Adaptive Behavior, pages 196202. MIT Press, 1992.
- arXiv:cs.LO/0309048v517Dec2006 TR IDSIA-19-03, Version 5
- Technical Report IDSIA-02-02 February 2002 January 2003 Optimality of Universal Bayesian Sequence
- BEYOND ``GENETIC PROGRAMMING'': INCREMENTAL SELFIMPROVEMENT
- SEQUENTIAL NEURAL TEXT COMPRESSION IEEE Transactions on Neural Networks, 7(1):142--146, 1996.
- AAAI Spring Symposium on Search under Uncertain and Incomplete Information, Stanford Univ. American Association for Artificial Intelligence, Menlo Park, Calif., 119124, 1999. Based on TR IDSIA5098, 1998.
- Machine Learning, 33, 105--115 (1998) fl 1998 Kluwer Academic Publishers, Boston. Manufactured in The Netherlands.
- A NOVEL UNSUPERVISED CLASSIFICATION METHOD In Proc. of the Intl. Conf. on Artificial Neural Networks, Brighton, pages 9196. IEE, 1993.
- Applying LSTM to Time Series Predictable Through Time-Window
- Learning Exploration Policies with Models Conference on Automated Learning and Discovery (CONALD'98)
- Co-Evolving Recurrent Neurons Learn Deep Memory Faustino J. Gomez1
- Learning The LongTerm Structure of the Blues #
- LOCOCODE versus PCA and ICA Sepp Hochreiter
- Feature extraction through LOCOCODE Sepp Hochreiter
- Technical Report IDSIA-13-01 15 December 2001 Distribution of Mutual Information
- Unsupervised coding with LOCOCODE Sepp Hochreiter and Jurgen Schmidhuber
- Speeding up Q()learning In Proceedings of the Tenth European Conference on Machine Learning (ECML'98)
- Technical Report IDSIA-20-00, Version 2.0; 20 Dec 2000 The material of Sections 1-5 was published in: Hierarchies of generalized Kolmogorov com-
- A GENERAL METHOD FOR MULTIAGENT REINFORCEMENT LEARNING IN UNRESTRICTED ENVIRONMENTS
- LEARNING TO GENERATE ARTIFICIAL FOVEA TRAJECTORIES FOR TARGET DETECTION
- Towards a Universal Theory of Arti cial Intelligence based on Algorithmic Probability and Sequential Decision Theory
- LowComplexity Coding and Decoding Sepp Hochreiter and Jurgen Schmidhuber
- Towards Practical Universal Search Tom Schaul and Jurgen Schmidhuber
- arXiv:0709.0674v1[cs.AI]5Sep2007 Simple Algorithmic Principles of Discovery,
- Technical Report IDSIA-11-00, 14. November 2000 New Error Bounds for Solomonoff Prediction
- In P. Angeline, Z. Michalewicz, M. Schoenauer, X. Yao, Z. Zalzala, eds., Congress on Evolutionary Computation, p. 16121618, IEEE Press, Piscataway, NJ, 1999.
- AN `INTROSPECTIVE' NETWORK THAT CAN LEARN TO RUN ITS OWN WEIGHT CHANGE ALGORITHM
- LOCOCODE PERFORMS NONLINEAR ICA WITHOUT KNOWING THE NUMBER OF SOURCES
- arXiv:cs.AI/0302012 The New AI
- DIRECT POLICY SEARCH AND UNCERTAIN POLICY EVALUATION
- Evolutionary Computation versus Reinforcement Learning
- COMPRESSING TEXTS WITH NEURAL NETS \Lambda Jurgen Schmidhuber
- Kalman lters improve LSTM network performance in problems unsolvable by
- arXiv:cs.LO/0309048v125Sep2003 TR IDSIA-19-03, Version 1.0; arXiv:cs.LO/0309048 v1, 25 September 2003
- Marcus Hutter -1 -The Fastest and Shortest Algorithm An effective Procedure for
- MH -1 -How to Predict with Bayes and MDL How to Predict with
- General Loss Bounds for Universal Sequence Prediction Marcus Hutter
- MULTIAGENT LEARNING WITH THE SUCCESSSTORY ALGORITHM
- LEARNING FACTORIAL CODES BY PREDICTABILITY MINIMIZATION
- Technical Report IDSIA0202 -28 February 2002 --16 January 2003 Optimality of Universal Bayesian Sequence
- Learning Context Sensitive Languages with LSTM Trained with Kalman Filters ?
- Felix A. Gers, gers@mantik.de, Neue Gruenstrasse 18, 10179 Berlin, Germany, www.mantik.de
- C J. Schmidhuber, 1994. LOWCOMPLEXITY ART
- Reinforcement Learning in Markovian and NonMarkovian Environments
- !#" $%&' ()0 1"32 4 5()768@9 A2 $% "CB 2 D0 E9F D0 8 $%(G!H
- Learning Nonregular Languages: A Comparison of Simple Recurrent Networks
- Finding Temporal Structure in Music: Blues Improvisation with LSTM Recurrent Networks #
- REINFORCEMENT LEARNING WITH SELFMODIFYING POLICIES
- Learning to Forget: Continual Prediction with Technical Report IDSIA0199
- ADAPTIVE DECOMPOSITION OF TIME (To appear in O. Simula, editor, Proceedings of the International Conference
- Matteo Gagliolo Jurgen Schmidhuber Learning Dynamic Algorithm Portfolios
- arXiv:cs.LO/0309048v311Dec2003 TR IDSIA-19-03, Version 3
- Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks
- TR IDSIA-12-02, Version 1.0; arXiv:cs.AI/0207097 v1, 31 July 2002 OPTIMAL ORDERED PROBLEM SOLVER
- LSTM Recurrent Networks Learn Simple Context Free and Context Sensitive Languages
- On Learning Soccer Strategies Rafa/l Sa/lustowicz, Marco Wiering, Jurgen Schmidhuber
- Gradient Flow in Recurrent Nets: the Difficulty of Learning LongTerm
- Measuring and Optimizing Behavioral Faustino J. Gomez, Julian Togelius, and Juergen Schmidhuber
- Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks
- Biologically Plausible Speech Recognition with LSTM Neural Nets
- Applied Mathematics Letters 22 (2009) 10291032 Contents lists available at ScienceDirect
- Evolino: Hybrid Neuroevolution / Optimal Linear Search for Sequence Learning Jurgen Schmidhuber1,2
- Godel Machines: Towards a Technical Justification of Consciousness
- Automatic discrimination among languages based on prosody Fred Cummins \Lambda , Felix Gers, Juergen Schmidhuber
- arXiv:cs.LO/0309048 TR IDSIA-19-03, Version 2; arXiv:cs.LO/0309048 v2, 28 October 2003
- DISCOVERING PREDICTABLE CLASSIFICATIONS (Neural Computation, 5(4):625--635, 1993)
- arXiv:quantph/0011122 Technical Report IDSIA2000, Version 2.0; 20 Dec 2000
- Technical Report IDSIA-16-00, 3 March 2001 ftp://ftp.idsia.ch/pub/techrep/IDSIA-16-00.ps.gz
- arXiv:cs.LO/0309048 TR IDSIA-19-03, Version 3
- Probabilistic Incremental Program Evolution: Stochastic Search Through Program Space
- In Proceedings of the European Conference on Machine Learning (ECML 2006) Efficient Non-Linear Control through
- Robust player imitation using multiobjective evolution Niels van Hoorn, Julian Togelius, Daan Wierstra and Jurgen Schmidhuber
- Quasi-Online Reinforcement Learning for Robots Bram Bakker, Viktor Zhumatiy, Gabriel Gruener, and Jurgen Schmidhuber
- SIMPLE PRINCIPLES OF METALEARNING Technical Report IDSIA6996
- HQLEARNING: DISCOVERING MARKOVIAN SUBGOALS FOR NONMARKOVIAN
- NEURAL PREDICTORS FOR DETECTING AND REMOVING REDUNDANT
- Sequential Decision Making Based on Direct Search
- ENVIRONMENTINDEPENDENT REINFORCEMENT ACCELERATION
- LEARNING TO CONTROL FASTWEIGHT MEMORIES: AN ALTERNATIVE TO DYNAMIC RECURRENT NETWORKS
- Learning Team Strategies With Multiple PolicySharing Agents: A Soccer Case Study
- A NEURAL NETWORK THAT EMBEDS ITS OWN METALEVELS In Proc. of the International Conference on Neural Networks '93, San Francisco. IEEE, 1993.
- Learning Algorithms for Networks with Internal and External Feedback
- In Neural Network World 3(6):849853, 1993. ``NEURAL'' REDUNDANCY REDUCTION
- arXiv:cs.LO/0309048 TR IDSIA-19-03, Version 1.0; arXiv:cs.LO/0309048 v1, 25 September 2003
- Journal of Machine Learning Research 11 (2010) 743-746 Submitted 11/09; Published 2/10 Tom Schaul TOM@IDSIA.CH
- Stochastic Search using the Natural Gradient Sun Yi yi@idsia.ch
- PREDICTIVE CODING WITH NEURAL NETS: APPLICATION TO
- International Journal of Foundations of Computer Science World Scienti c Publishing Company
- Towards Compositional Learning in Dynamic Networks Technical Report FKI12990
- The Neural Bucket Brigade In R. Pfeifer, Z. Schreter, Z. Fogelman, and L. Steels, editors, Connectionism in Perspective, pages
- Technical Report IDSIA-04-02 17 April 2002 Proceedings of COLT-2002 Self-Optimizing and Pareto-Optimal Policies in
- Probabilistic Incremental Program Evolution Rafa/l Sa/lustowicz and Jurgen Schmidhuber
- The Neural Heat Exchanger ``Invited Talk'' at ICONIP'96
- Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior (SAB'98): From Animals to Animats 5, 223228, R. Pfeiffer, B. Blumberg, J. A. Meyer and S. W. Wilson (eds.)
- Evolving strategies for active flow control Michele Milano
- MODEL-BASED REINFORCEMENT LEARNING FOR EVOLVING SOCCER
- Learning Restart Strategies Matteo Gagliolo
- arXiv:cs.AI/0207097v223Dec2002 Technical Report IDSIA-12-02, Version 2.0 (arXiv:cs.AI/0207097 v2) 1-43 December 23, 2002 Optimal Ordered Problem Solver
- BiasOptimal Incremental Problem Solving urgen Schmidhuber
- USING ADAPTIVE SEQUENTIAL NEUROCONTROL FOR EFFICIENT LEARNING OF TRANSLATION AND ROTATION INVARIANCE
- Solving a Complex Prisoner's Dilemma with SelfModifying Policies
- Technical Report IDSIA-12-02, Version 2.0 (arXiv:cs.AI/0207097 v2) 1-43 December 23, 2002 Optimal Ordered Problem Solver
- From Network: Comput. Neural Syst. 10 (1999) 133169. c fl 1999 IOP Publishing Ltd
- NONLINEAR ICA THROUGH LOWCOMPLEXITY AUTOENCODERS Sepp Hochreiter
- A Python Experiment Suite THOMAS RUCKSTIE
- Framewise Phoneme Classification with Bidirectional LSTM Networks
- Modeling Systems with Internal State using Evolino Daan Wierstra1
- A Neural Network Model for Inter-problem Adaptive Online Time Allocation
- Bias-Optimal Incremental Learning of Control Sequences for Virtual Robots
- A Comparison Between Spiking and Differentiable Recurrent Neural Networks on Spoken Digit Recognition
- Fitness Expectation Maximization Daan Wierstra1
- PALADYN Journal of Behavioral Robotics Review Article DOI: 10.2478/s13230-010-0002-4 JBR 1(1) 2010 14-24
- Book Editors IOS Press, 2003
- The New AI is General & Mathematically Rigorous Jurgen Schmidhuber
- Information and Computation 205 (2007) 242261 www.elsevier.com/locate/ic
- UNSUPERVISED EXTRACTION OF PREDICTABLE ABSTRACT FEATURES
- Recent Progress in the Fields of Universal Learning Algorithms and Optimal Search
- DISCOVERING NEURAL NETS WITH LOW KOLMOGOROV COMPLEXITY AND
- In C. Freksa, ed., Foundations of Computer Science: Potential Theory Cognition Lecture Notes in Computer Science, pp. 201208, Springer, 1997.
- Evolving Soccer Strategies Rafa/l Sa/lustowicz, Marco Wiering, Jurgen Schmidhuber
- Hierarchical Reinforcement Learning with Subpolicies Specializing for Learned Subgoals
- Technical Report IDSIA-09-01 15 August 2001 16 January 2003 Convergence and Loss Bounds for
- Self-Motivated Development Through Rewards for Predictor Errors / Improvements
- Classifying Unprompted Speech by Retraining Nicole Beringer1
- Searching for Minimal Neural Networks in Fourier Space Jan Koutnik, Faustino Gomez, and Jurgen Schmidhuber
- Convolutional Neural Network Committees For Handwritten Character Classification
- Incremental Basis Construction from Temporal Difference Error Yi Sun yi@idsia.ch
- Sequential Constant Size Compressors for Reinforcement Learning
- Coherence Progress: A Measure of Interestingness Based on Fixed Compressors
- Incremental Slow Feature Analysis Varun Raj Kompella, Matthew Luciw, and Jurgen Schmidhuber
- A Family of Godel Machine Implementations Bas R. Steunebrink and Jurgen Schmidhuber
- The Two-Dimensional Organization of Behavior Mark Ring, Tom Schaul, Juergen Schmidhuber
- Policy Gradients for Cryptanalysis Frank Sehnke1
- Curiosity-Driven Optimization University of Lugano
- On Fast Deep Nets for AGI Vision Jurgen Schmidhuber, Dan Ciresan, Ueli Meier, Jonathan Masci, Alex Graves
- Better digit recognition with a committee of simple Neural Nets Ueli Meier and Dan Claudiu Ciresan and Luca Maria Gambardella and Jurgen Schmidhuber
- Optimal Direct Policy Search Tobias Glasmachers and Jurgen Schmidhuber
- Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments
- A Natural Evolution Strategy for Multi-Objective Optimization
- High Dimensions and Heavy Tails for Natural Evolution Strategies
- Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction
- Modular Deep Belief Networks that do not Forget Leo Pape, Faustino Gomez, Mark Ring and Jurgen Schmidhuber
- Unsupervised Modeling of Partially Observable Environments
- Multi-Dimensional Deep Memory Go-Player for Parameter Exploring Policy Gradients
- Evolving Neural Networks in Compressed Weight Space Jan Koutnk
- Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices
- Intrinsically Motivated NeuroEvolution for Vision-Based Reinforcement Learning
- A Committee of Neural Networks for Traffic Sign Classification Dan Ciresan, Ueli Meier, Jonathan Masci and Jurgen Schmidhuber
- Artificial Curiosity with Planning for Autonomous Perceptual and Cognitive Development
