Jürgen Schmidhuber

Affiliations:
  • King Abdullah University of Science and Technology (KAUST), Saudi Arabia
  • University of Applied Sciences and Arts of Southern Switzerland, Switzerland (former)


According to our database1, Jürgen Schmidhuber authored at least 402 papers between 1987 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Real World Music Object Recognition.
Trans. Int. Soc. Music. Inf. Retr., January, 2024

2023
Unsupervised Learning of Temporal Abstractions With Slot-Based Transformers.
Neural Comput., 2023

SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention.
CoRR, 2023

Automating Continual Learning.
CoRR, 2023

Efficient Rotation Invariance in Deep Neural Networks through Artificial Mental Rotation.
CoRR, 2023

Unsupervised Musical Object Discovery from Audio.
CoRR, 2023

The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute.
CoRR, 2023

Learning to Identify Critical States for Reinforcement Learning from Videos.
CoRR, 2023

Exploring the Promise and Limits of Real-Time Recurrent Learning.
CoRR, 2023

Mindstorms in Natural Language-Based Societies of Mind.
CoRR, 2023

Large Language Model Programs.
CoRR, 2023

Accelerating Neural Self-Improvement via Bootstrapping.
CoRR, 2023

Topological Neural Discrete Representation Learning à la Kohonen.
CoRR, 2023

Guiding Online Reinforcement Learning with Action-Free Offline Pretraining.
CoRR, 2023

Contrastive Training of Complex-Valued Autoencoders for Object Discovery.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

The Benefits of Model-Based Generalization in Reinforcement Learning.
Proceedings of the International Conference on Machine Learning, 2023

Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Learning to Identify Critical States for Reinforcement Learning from Videos.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Approximating Two-Layer Feedforward Networks for Efficient Transformers.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

Goal-Conditioned Generators of Deep Policies.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
Analysis of Neural Network Based Proportional Myoelectric Hand Prosthesis Control.
IEEE Trans. Biomed. Eng., 2022

Bayesian Brains and the Rényi Divergence.
Neural Comput., 2022

Recurrent Neural-Linear Posterior Sampling for Nonstationary Contextual Bandits.
Neural Comput., 2022

Is it enough to optimize CNN architectures on ImageNet?
Frontiers Comput. Sci., 2022

Eliminating Meta Optimization Through Self-Referential Meta Learning.
CoRR, 2022

Learning One Abstract Bit at a Time Through Self-Invented Experiments Encoded as Neural Networks.
CoRR, 2022

Annotated History of Modern AI and Deep Learning.
CoRR, 2022

On Narrative Information and the Distillation of Stories.
CoRR, 2022

Learning to Control Rapidly Changing Synaptic Connections: An Alternative Type of Memory in Sequence Processing Artificial Neural Networks.
CoRR, 2022

Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter.
CoRR, 2022

General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States.
CoRR, 2022

Upside-Down Reinforcement Learning Can Diverge in Stochastic Environments With Episodic Resets.
CoRR, 2022

Learning Relative Return Policies With Upside-Down Reinforcement Learning.
CoRR, 2022

All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL.
CoRR, 2022

Exploring through Random Curiosity with General Value Functions.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

A Modern Self-Referential Weight Matrix That Learns to Modify Itself.
Proceedings of the International Conference on Machine Learning, 2022

The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention.
Proceedings of the International Conference on Machine Learning, 2022

The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization.
Proceedings of the Tenth International Conference on Learning Representations, 2022

CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

Reward-Weighted Regression Converges to a Global Optimum.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021
Deep neural network representation and Generative Adversarial Learning.
Neural Networks, 2021

Reinforcement Learning in Sparse-Reward Environments With Hindsight Policy Gradients.
Neural Comput., 2021

Improving Baselines in the Wild.
CoRR, 2021

Training and Generating Neural Networks in Compressed Weight Space.
CoRR, 2021

Automatic Embedding of Stories Into Collections of Independent Media.
CoRR, 2021

Linear Transformers Are Secretly Fast Weight Memory Systems.
CoRR, 2021

Meta Learning Backpropagation And Improving It.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Going Beyond Linear Transformers with Recurrent Fast Weight Programmers.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Improving Stateful Premise Selection with Transformers.
Proceedings of the Intelligent Computer Mathematics - 14th International Conference, 2021

Linear Transformers Are Secretly Fast Weight Programmers.
Proceedings of the 38th International Conference on Machine Learning, 2021

Learning Associative Inference Using Fast Weight Memory.
Proceedings of the 9th International Conference on Learning Representations, 2021

Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling.
Proceedings of the 9th International Conference on Learning Representations, 2021

Unsupervised Object Keypoint Learning using Local Spatial Predictability.
Proceedings of the 9th International Conference on Learning Representations, 2021

Parameter-Based Value Functions.
Proceedings of the 9th International Conference on Learning Representations, 2021

Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks.
Proceedings of the 9th International Conference on Learning Representations, 2021

The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

Hierarchical Relational Inference.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Investigating object compositionality in Generative Adversarial Networks.
Neural Networks, 2020

Generative Adversarial Networks are special cases of Artificial Curiosity (1990) and also closely related to Predictability Minimization (1991).
Neural Networks, 2020

On the Binding Problem in Artificial Neural Networks.
CoRR, 2020

Recurrent Neural-Linear Posterior Sampling for Non-Stationary Contextual Bandits.
CoRR, 2020

Parameter-based Value Functions.
CoRR, 2020

Deep Learning: Our Miraculous Year 1990-1991.
CoRR, 2020

Fusion Architectures for Word-Based Audiovisual Speech Recognition.
Proceedings of the Interspeech 2020, 2020

The DeepScoresV2 Dataset and Benchmark for Music Object Detection.
Proceedings of the 25th International Conference on Pattern Recognition, 2020

Improving Generalization in Meta Reinforcement Learning using Learned Objectives.
Proceedings of the 8th International Conference on Learning Representations, 2020

Motion Dynamics Improve Speaker-Independent Lipreading.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019
Training Agents using Upside-Down Reinforcement Learning.
CoRR, 2019

Reinforcement Learning Upside Down: Don't Predict Rewards - Just Map Them to Actions.
CoRR, 2019

Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving.
CoRR, 2019

R-SQAIR: Relational Sequential Attend, Infer, Repeat.
CoRR, 2019

Recurrent Neural Processes.
CoRR, 2019

Unsupervised Minimax: Adversarial Curiosity, Generative Adversarial Networks, and Predictability Minimization.
CoRR, 2019

A Perspective on Objects and Systematic Generalization in Model-Based RL.
CoRR, 2019

Are Disentangled Representations Helpful for Abstract Visual Reasoning?
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Hindsight policy gradients.
Proceedings of the 7th International Conference on Learning Representations, 2019

Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control.
Proceedings of the 7th International Conference on Learning Representations, 2019

Adaptation of an EMG-Based Speech Recognizer via Meta-Learning.
Proceedings of the 2019 IEEE Global Conference on Signal and Information Processing, 2019

2018
World Models.
CoRR, 2018

One Big Net For Everything.
CoRR, 2018

Learning to Reason with Third Order Tensor Products.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Recurrent World Models Facilitate Policy Evolution.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Deep Watershed Detector for Music Object Recognition.
Proceedings of the 19th International Society for Music Information Retrieval Conference, 2018

Domain-Adversarial Training for Session Independent EMG-based Speech Recognition.
Proceedings of the Interspeech 2018, 2018

DeepScores-A Dataset for Segmentation, Detection and Classification of Tiny Objects.
Proceedings of the 24th International Conference on Pattern Recognition, 2018

Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions.
Proceedings of the 6th International Conference on Learning Representations, 2018

Investigations on End- to-End Audiovisual Fusion.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017
Deep Learning.
Proceedings of the Encyclopedia of Machine Learning and Data Mining, 2017

LSTM: A Search Space Odyssey.
IEEE Trans. Neural Networks Learn. Syst., 2017

Hindsight policy gradients.
CoRR, 2017

Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots.
Artif. Intell., 2017

The Sacred Infrastructure for Computational Research.
Proceedings of the 16th Python in Science Conference 2017, 2017

Neural Expectation Maximization.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Improving Speaker-Independent Lipreading with Domain-Adversarial Training.
Proceedings of the Interspeech 2017, 2017

Recurrent Highway Networks.
Proceedings of the 34th International Conference on Machine Learning, 2017

Highway and Residual Networks learn Unrolled Iterative Estimation.
Proceedings of the 5th International Conference on Learning Representations, 2017

2016
A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots.
IEEE Robotics Autom. Lett., 2016

Optimal Curiosity-Driven Modular Incremental Slow Feature Analysis.
Neural Comput., 2016

Discovering Boolean Gates in Slime Mould.
CoRR, 2016

Tagger: Deep Unsupervised Perceptual Grouping.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Deep Neural Network Frontend for Continuous EMG-Based Speech Recognition.
Proceedings of the Interspeech 2016, 2016

Lipreading with long short-term memory.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

A Wavelet-based Encoding for Neuroevolution.
Proceedings of the 2016 on Genetic and Evolutionary Computation Conference, Denver, CO, USA, July 20, 2016

Growing Recursive Self-Improvers.
Proceedings of the Artificial General Intelligence - 9th International Conference, 2016

2015
Deep Learning.
Scholarpedia, 2015

Deep learning in neural networks: An overview.
Neural Networks, 2015

Assessment of algorithms for mitosis detection in breast cancer histopathology images.
Medical Image Anal., 2015

Understanding Locally Competitive Networks.
Proceedings of the 3rd International Conference on Learning Representations, 2015

Highway Networks.
CoRR, 2015

On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models.
CoRR, 2015

Binding via Reconstruction Clustering.
CoRR, 2015

Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Training Very Deep Networks.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

The Natural Gradient as a control signal for a humanoid robot.
Proceedings of the 15th IEEE-RAS International Conference on Humanoid Robots, 2015

Anytime Bounded Rationality.
Proceedings of the Artificial General Intelligence, 2015

2014
Descriptor Learning for Omnidirectional Image Matching.
Proceedings of the Registration and Recognition in Images and Videos, 2014

Efficient Interactive Multiclass Learning from Binary Feedback.
ACM Trans. Interact. Intell. Syst., 2014

Multimodal Similarity-Preserving Hashing.
IEEE Trans. Pattern Anal. Mach. Intell., 2014

Natural evolution strategies.
J. Mach. Learn. Res., 2014

Rapid Humanoid Motion Learning through Coordinated, Parallel Evolution.
Proceedings of the From Animals to Animats 13, 2014

Reinforcement-Driven Shaping of Sequence Learning in Neural Dynamics.
Proceedings of the From Animals to Animats 13, 2014

Online Evolution of Deep Convolutional Network for Vision-Based Reinforcement Learning.
Proceedings of the From Animals to Animats 13, 2014

An Anti-hebbian Learning Rule to Represent Drive Motivations for Reinforcement Learning.
Proceedings of the From Animals to Animats 13, 2014

Deep Networks with Internal Selective Attention through Feedback Connections.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Candidate Sampling for Neuron Reconstruction from Anisotropic Electron Microscopy Volumes.
Proceedings of the Medical Image Computing and Computer-Assisted Intervention - MICCAI 2014, 2014

A comparison of algorithms and humans for mitosis detection.
Proceedings of the IEEE 11th International Symposium on Biomedical Imaging, 2014

Improving robot vision models for object detection through interaction.
Proceedings of the 2014 International Joint Conference on Neural Networks, 2014

Explore to see, learn to perceive, get the actions for free: SKILLABILITY.
Proceedings of the 2014 International Joint Conference on Neural Networks, 2014

A Clockwork RNN.
Proceedings of the 31th International Conference on Machine Learning, 2014

Reactive Reaching and Grasping on a Humanoid - Towards Closing the Action-Perception Loop on the iCub.
Proceedings of the ICINCO 2014 - Proceedings of the 11th International Conference on Informatics in Control, Automation and Robotics, Volume 1, Vienna, Austria, 1, 2014

Reinforcement and shaping in learning action sequences with neural dynamics.
Proceedings of the 4th International Conference on Development and Learning and on Epigenetic Robotics, 2014

Human-robot cooperation: fast, interactive learning from binary feedback.
Proceedings of the ACM/IEEE International Conference on Human-Robot Interaction, 2014

Evolving deep unsupervised convolutional networks for vision-based reinforcement learning.
Proceedings of the Genetic and Evolutionary Computation Conference, 2014


2013
PUF Modeling Attacks on Simulated and Silicon Data.
IEEE Trans. Inf. Forensics Secur., 2013

An intrinsic value system for developing multiple invariant representations with incremental slowness learning.
Frontiers Neurorobotics, 2013

Curiosity driven reinforcement learning for motion planning on humanoids.
Frontiers Neurorobotics, 2013

Testing Hypotheses by Regularized Maximum Mean Discrepancy
CoRR, 2013

My First Deep Learning System of 1991 + Deep Learning Timeline 1962-2013.
CoRR, 2013

Bounded Recursive Self-Improvement.
CoRR, 2013

Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification.
CoRR, 2013

Compete to Compute.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks.
Proceedings of the Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013, 2013

A Learning Framework for Morphological Operators Using Counter-Harmonic Mean.
Proceedings of the Mathematical Morphology and Its Applications to Signal and Image Processing, 2013

Task-relevant roadmaps: A framework for humanoid motion planning.
Proceedings of the 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013

Multi-scale pyramidal pooling network for generic steel defect classification.
Proceedings of the 2013 International Joint Conference on Neural Networks, 2013

Artificial neural networks for spatial perception: Towards visual object localisation in humanoid robots.
Proceedings of the 2013 International Joint Conference on Neural Networks, 2013

Upper Confidence Weighted Learning for Efficient Exploration in Multiclass Prediction with Binary Feedback.
Proceedings of the IJCAI 2013, 2013

A fast learning algorithm for image segmentation with max-pooling convolutional networks.
Proceedings of the IEEE International Conference on Image Processing, 2013

Fast image scanning with deep max-pooling convolutional neural networks.
Proceedings of the IEEE International Conference on Image Processing, 2013

A linear time natural evolution strategy for non-separable functions.
Proceedings of the Genetic and Evolutionary Computation Conference, 2013

Evolving large-scale neural networks for vision-based reinforcement learning.
Proceedings of the Genetic and Evolutionary Computation Conference, 2013

Evolving large-scale neural networks for vision-based TORCS.
Proceedings of the 8th International Conference on the Foundations of Digital Games, 2013

Humanoid learns to detect its own hands.
Proceedings of the IEEE Congress on Evolutionary Computation, 2013

Resource-Bounded Machines are Motivated to be Effective, Efficient, and Curious.
Proceedings of the Artificial General Intelligence - 6th International Conference, 2013

Maximizing Fun by Creating Data with Easily Reducible Subjective Complexity.
Proceedings of the Intrinsically Motivated Learning in Natural and Artificial Systems, 2013

2012
Deep Big Multilayer Perceptrons for Digit Recognition.
Proceedings of the Neural Networks: Tricks of the Trade - Second Edition, 2012

Multi-column deep neural network for traffic sign classification.
Neural Networks, 2012

Incremental Slow Feature Analysis: Adaptive Low-Complexity Slow Feature Updating from High-Dimensional Input Streams.
Neural Comput., 2012

Turing: Keep his work in perspective.
Nat., 2012

Learning tactile skills through curious exploration.
Frontiers Neurorobotics, 2012

Kernel representations for evolving continuous functions.
Evol. Intell., 2012

Correction: novel Kernel-based recognizers of human actions.
EURASIP J. Adv. Signal Process., 2012

A Frequency-Domain Encoding for Neuroevolution
CoRR, 2012

First Experiments with PowerPlay
CoRR, 2012

Self-Delimiting Neural Networks
CoRR, 2012

Object Recognition with Multi-Scale Pyramidal Pooling Networks
CoRR, 2012

T-Learning
CoRR, 2012

Incremental learning using partial feedback for gesture-based human-swarm interaction.
Proceedings of the 21st IEEE International Symposium on Robot and Human Interactive Communication, 2012

Generalized Compressed Network Search.
Proceedings of the Parallel Problem Solving from Nature - PPSN XII, 2012

Compressed Network Complexity Search.
Proceedings of the Parallel Problem Solving from Nature - PPSN XII, 2012

Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images.
Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

Transferring spatial perception between robots operating in a shared workspace.
Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012

Learning skills from play: Artificial curiosity on a Katana robot arm.
Proceedings of the 2012 International Joint Conference on Neural Networks (IJCNN), 2012

Steel defect classification with Max-Pooling Convolutional Neural Networks.
Proceedings of the 2012 International Joint Conference on Neural Networks (IJCNN), 2012

Transfer learning for Latin and Chinese characters with Deep Neural Networks.
Proceedings of the 2012 International Joint Conference on Neural Networks (IJCNN), 2012

On the Size of the Online Kernel Sparsification Dictionary.
Proceedings of the 29th International Conference on Machine Learning, 2012

The Modular Behavioral Environment for Humanoids and other Robots (MoBeE).
Proceedings of the ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics, Volume 2, Rome, Italy, 28, 2012

Continually adding self-invented problems to the repertoire: First experiments with POWERPLAY.
Proceedings of the 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics, 2012

Autonomous learning of robust visual object detection and identification on a humanoid.
Proceedings of the 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics, 2012

Autonomous learning of abstractions using Curiosity-Driven Modular Incremental Slow Feature Analysis.
Proceedings of the 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics, 2012

Autonomous reinforcement of behavioral sequences in neural dynamics.
Proceedings of the 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics, 2012

Low Complexity Proto-Value Function Learning from Sensory Observations with Incremental Slow Feature Analysis.
Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2012, 2012

Reflexive Collision Response with Virtual Skin - Roadmap Planning Meets Reinforcement Learning.
Proceedings of the ICAART 2012 - Proceedings of the 4th International Conference on Agents and Artificial Intelligence, Volume 1, 2012

MT-CGP: mixed type cartesian genetic programming.
Proceedings of the Genetic and Evolutionary Computation Conference, 2012

Complexity search for compressed neural networks.
Proceedings of the Genetic and Evolutionary Computation Conference, 2012

Multi-column deep neural networks for image classification.
Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

An Integrated, Modular Framework for Computer Vision and Cognitive Robotics Research (icVision).
Proceedings of the Biologically Inspired Cognitive Architectures 2012 - Proceedings of the Third Annual Meeting of the BICA Society, Palermo, Sicily, Italy, October 31, 2012

Modular Value Iteration through Regional Decomposition.
Proceedings of the Artificial General Intelligence - 5th International Conference, 2012

2011
Descriptor learning for omnidirectional image matching
CoRR, 2011

POWERPLAY: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem
CoRR, 2011

Incremental Slow Feature Analysis: Adaptive and Episodic Learning from High-Dimensional Input Streams
CoRR, 2011

Measuring Intelligence through Games
CoRR, 2011

Natural Evolution Strategies
CoRR, 2011

Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs
CoRR, 2011

High-Performance Neural Networks for Visual Object Classification
CoRR, 2011

Algorithm portfolio selection as a bandit problem with unbounded losses.
Ann. Math. Artif. Intell., 2011

Unsupervised Modeling of Partially Observable Environments.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2011

Modular deep belief networks that do not forget.
Proceedings of the 2011 International Joint Conference on Neural Networks, 2011

A committee of neural networks for traffic sign classification.
Proceedings of the 2011 International Joint Conference on Neural Networks, 2011

Incremental Slow Feature Analysis.
Proceedings of the IJCAI 2011, 2011

Flexible, High Performance Convolutional Neural Networks for Image Classification.
Proceedings of the IJCAI 2011, 2011

Max-pooling convolutional neural networks for vision-based hand gesture recognition.
Proceedings of the 2011 IEEE International Conference on Signal and Image Processing Applications, 2011

Incremental Basis Construction from Temporal Difference Error.
Proceedings of the 28th International Conference on Machine Learning, 2011

The two-dimensional organization of behavior.
Proceedings of the 1st International Conference on Development and Learning and on Epigenetic Robotics, 2011

Artificial curiosity with planning for autonomous perceptual and cognitive development.
Proceedings of the 1st International Conference on Development and Learning and on Epigenetic Robotics, 2011

Intrinsically motivated neuroevolution for vision-based reinforcement learning.
Proceedings of the 1st International Conference on Development and Learning and on Epigenetic Robotics, 2011

Better Digit Recognition with a Committee of Simple Neural Nets.
Proceedings of the 2011 International Conference on Document Analysis and Recognition, 2011

Convolutional Neural Network Committees for Handwritten Character Classification.
Proceedings of the 2011 International Conference on Document Analysis and Recognition, 2011

Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction.
Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2011, 2011

AutoIncSFA and vision-based developmental learning for humanoid robots.
Proceedings of the 11th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2011), 2011

High dimensions and heavy tails for natural evolution strategies.
Proceedings of the 13th Annual Genetic and Evolutionary Computation Conference, 2011

Curiosity-driven optimization.
Proceedings of the IEEE Congress on Evolutionary Computation, 2011

Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments.
Proceedings of the Artificial General Intelligence - 4th International Conference, 2011

A Family of Gödel Machine Implementations.
Proceedings of the Artificial General Intelligence - 4th International Conference, 2011

On Fast Deep Nets for AGI Vision.
Proceedings of the Artificial General Intelligence - 4th International Conference, 2011

Coherence Progress: A Measure of Interestingness Based on Fixed Compressors.
Proceedings of the Artificial General Intelligence - 4th International Conference, 2011

Optimal Direct Policy Search.
Proceedings of the Artificial General Intelligence - 4th International Conference, 2011

Sequential Constant Size Compressors for Reinforcement Learning.
Proceedings of the Artificial General Intelligence - 4th International Conference, 2011

Lifelong Credit Assignment with the Success-Story Algorithm.
Proceedings of the Lifelong Learning, 2011

2010
Formal Theory of Creativity, Fun, and Intrinsic Motivation (1990-2010).
IEEE Trans. Auton. Ment. Dev., 2010

Metalearning.
Scholarpedia, 2010

Exploring parameter space in reinforcement learning.
Paladyn J. Behav. Robotics, 2010

Parameter-exploring policy gradients.
Neural Networks, 2010

Deep, Big, Simple Neural Nets for Handwritten Digit Recognition.
Neural Comput., 2010

PyBrain.
J. Mach. Learn. Res., 2010

Recurrent policy gradients.
Log. J. IGPL, 2010

Modeling Attacks on Physical Unclonable Functions.
IACR Cryptol. ePrint Arch., 2010

Novel Kernel-Based Recognizers of Human Actions.
EURASIP J. Adv. Signal Process., 2010

Evolution of National Nobel Prize Shares in the 20th Century
CoRR, 2010

Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition
CoRR, 2010

A Natural Evolution Strategy for Multi-objective Optimization.
Proceedings of the Parallel Problem Solving from Nature, 2010

Formal Theory of Fun and Creativity.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2010

Characteristic Kernels on Structured Domains Excel in Robotics and Human Action Recognition.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2010

Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices.
Proceedings of the Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, 2010

Algorithm Selection as a Bandit Problem with Unbounded Losses.
Proceedings of the Learning and Intelligent Optimization, 4th International Conference, 2010

Multimodal Parameter-exploring Policy Gradients.
Proceedings of the Ninth International Conference on Machine Learning and Applications, 2010

Policy Gradients for Cryptanalysis.
Proceedings of the Artificial Neural Networks - ICANN 2010, 2010

Multi-Dimensional Deep Memory Atari-Go Players for Parameter Exploring Policy Gradients.
Proceedings of the Artificial Neural Networks, 2010

Evolving neural networks in compressed weight space.
Proceedings of the Genetic and Evolutionary Computation Conference, 2010

Exponential natural evolution strategies.
Proceedings of the Genetic and Evolutionary Computation Conference, 2010

Robust Texture Recognition Using Credal Classifiers.
Proceedings of the British Machine Vision Conference, 2010

2009
A Novel Connectionist System for Unconstrained Handwriting Recognition.
IEEE Trans. Pattern Anal. Mach. Intell., 2009

Ontogenetic and Phylogenetic Reinforcement Learning.
Künstliche Intell., 2009

On-Chip Electric Waves: An Analog Circuit Approach to Physical Uncloneable Functions.
IACR Cryptol. ePrint Arch., 2009

A reinforcement learning approach for individualizing erythropoietin dosages in hemodialysis patients.
Expert Syst. Appl., 2009

Ultimate Cognition <i>à la</i> Gödel.
Cogn. Comput., 2009

Using data compressors to construct order tests for homogeneity and component independence.
Appl. Math. Lett., 2009

Stochastic search using the natural gradient.
Proceedings of the 26th Annual International Conference on Machine Learning, 2009

An EM Based Training Algorithm for Recurrent Neural Networks.
Proceedings of the Artificial Neural Networks, 2009

Scalable Neural Networks for Board Games.
Proceedings of the Artificial Neural Networks, 2009

Measuring and Optimizing Behavioral Complexity for Evolutionary Reinforcement Learning.
Proceedings of the Artificial Neural Networks, 2009

Evolving Memory Cell Structures for Sequence Learning.
Proceedings of the Artificial Neural Networks, 2009

Efficient natural evolution strategies.
Proceedings of the Genetic and Evolutionary Computation Conference, 2009

Super mario evolution.
Proceedings of the 2009 IEEE Symposium on Computational Intelligence and Games, 2009

Hierarchical controller learning in a First-Person Shooter.
Proceedings of the 2009 IEEE Symposium on Computational Intelligence and Games, 2009

Robust player imitation using multiobjective evolution.
Proceedings of the IEEE Congress on Evolutionary Computation, 2009

2008
Accelerated Neural Evolution through Cooperatively Coevolved Synapses.
J. Mach. Learn. Res., 2008

Phoneme recognition in TIMIT with BLSTM-CTC
CoRR, 2008

A System for Robotic Heart Surgery that Learns to Tie Knots Using Recurrent Neural Networks.
Adv. Robotics, 2008

Fitness Expectation Maximization.
Proceedings of the Parallel Problem Solving from Nature, 2008

Countering Poisonous Inputs with Memetic Neuroevolution.
Proceedings of the Parallel Problem Solving from Nature, 2008

State-Dependent Exploration for Policy Gradient Methods.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2008

Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 21, 2008

Driven by Compression Progress.
Proceedings of the Knowledge-Based Intelligent Information and Engineering Systems, 2008

Episodic Reinforcement Learning by Logistic Reward-Weighted Regression.
Proceedings of the Artificial Neural Networks, 2008

Policy Gradients with Parameter-Based Exploration for Control.
Proceedings of the Artificial Neural Networks, 2008

Towards Distributed Algorithm Portfolios.
Proceedings of the International Symposium on Distributed Computing and Artificial Intelligence, 2008

An experiment in automatic game design.
Proceedings of the 2008 IEEE Symposium on Computational Intelligence and Games, 2008

A scalable neural network architecture for board games.
Proceedings of the 2008 IEEE Symposium on Computational Intelligence and Games, 2008

Generating diverse opponents with multiobjective evolution.
Proceedings of the 2008 IEEE Symposium on Computational Intelligence and Games, 2008

Natural Evolution Strategies.
Proceedings of the IEEE Congress on Evolutionary Computation, 2008

Learning what to ignore: Memetic climbing in topology and weight space.
Proceedings of the IEEE Congress on Evolutionary Computation, 2008

Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes.
Proceedings of the Anticipatory Behavior in Adaptive Learning Systems, 2008

2007
New Millennium AI and the Convergence of History.
Proceedings of the Challenges for Computational Intelligence, 2007

Gödel Machines: Fully Self-referential Optimal Universal Self-improvers.
Proceedings of the Artificial General Intelligence, 2007

The New AI: General & Sound & Relevant for Physics.
Proceedings of the Artificial General Intelligence, 2007

Training Recurrent Networks by Evolino.
Neural Comput., 2007

Algorithmic complexity bounds on future prediction errors.
Inf. Comput., 2007

Using Data Compressors to Construct Rank Tests
CoRR, 2007

Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007

Learning Restart Strategies.
Proceedings of the IJCAI 2007, 2007

Sequence Labelling in Structured Domains with Hierarchical Recurrent Neural Networks.
Proceedings of the IJCAI 2007, 2007

Solving Deep Memory POMDPs with Recurrent Policy Gradients.
Proceedings of the Artificial Neural Networks, 2007

Multi-dimensional Recurrent Neural Networks.
Proceedings of the Artificial Neural Networks, 2007

An Application of Recurrent Neural Networks to Discriminative Keyword Spotting.
Proceedings of the Artificial Neural Networks, 2007

RNN-based Learning of Compact Maps for Efficient Robot Localization.
Proceedings of the 15th European Symposium on Artificial Neural Networks, 2007

Policy Gradient Critics.
Proceedings of the Machine Learning: ECML 2007, 2007

Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity.
Proceedings of the Discovery Science, 10th International Conference, 2007

Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity and Creativity.
Proceedings of the Algorithmic Learning Theory, 18th International Conference, 2007

2006
New Millennium AI and the Convergence of History
CoRR, 2006

Developmental robotics, optimal artificial curiosity, creativity, music, and the fine arts.
Connect. Sci., 2006

Learning dynamic algorithm portfolios.
Ann. Math. Artif. Intell., 2006

Dynamic Algorithm Portfolios.
Proceedings of the International Symposium on Artificial Intelligence and Mathematics, 2006

Quasi-online Reinforcement Learning for Robots.
Proceedings of the 2006 IEEE International Conference on Robotics and Automation, 2006

Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks.
Proceedings of the Machine Learning, 2006

Metric State Space Reinforcement Learning for a Vision-Capable Mobile Robot.
Proceedings of the Intelligent Autonomous Systems 9, 2006

Evolino for recurrent support vector machines.
Proceedings of the 14th European Symposium on Artificial Neural Networks, 2006

Efficient Non-linear Control Through Neuroevolution.
Proceedings of the Machine Learning: ECML 2006, 2006

Complexity Monotone in Conditions and Future Prediction Errors.
Proceedings of the Kolmogorov Complexity and Applications, 29.01. - 03.02.2006, 2006

Impact of Censored Sampling on the Performance of Restart Strategies.
Proceedings of the Principles and Practice of Constraint Programming, 2006

Prefix-Like Complexities and Computability in the Limit.
Proceedings of the Logical Approaches to Computational Barriers, 2006

2006: Celebrating 75 Years of AI - History and Outlook: The Next 25 Years.
Proceedings of the 50 Years of Artificial Intelligence, 2006

2005
Framewise phoneme classification with bidirectional LSTM and other neural network architectures.
Neural Networks, 2005

Evolino: Hybrid Neuroevolution/Optimal Linear Search for Sequence Learning.
Proceedings of the IJCAI-05, Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, Edinburgh, Scotland, UK, July 30, 2005

Completely Self-referential Optimal Reinforcement Learners.
Proceedings of the Artificial Neural Networks: Formal Models and Their Applications, 2005

Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition.
Proceedings of the Artificial Neural Networks: Formal Models and Their Applications, 2005

Evolving Modular Fast-Weight Networks for Control.
Proceedings of the Artificial Neural Networks: Formal Models and Their Applications, 2005

Fast Color-Based Object Recognition Independent of Position and Orientation.
Proceedings of the Artificial Neural Networks: Biological Inspirations, 2005

A Neural Network Model for Inter-problem Adaptive Online Time Allocation.
Proceedings of the Artificial Neural Networks: Formal Models and Their Applications, 2005

Classifying Unprompted Speech by Retraining LSTM Nets.
Proceedings of the Artificial Neural Networks: Biological Inspirations, 2005

Modeling systems with internal state using evolino.
Proceedings of the Genetic and Evolutionary Computation Conference, 2005

Co-evolving recurrent neurons learn deep memory POMDPs.
Proceedings of the Genetic and Evolutionary Computation Conference, 2005

Gödel Machines: Towards a Technical Justification of Consciousness.
Proceedings of the Adaptive Agents and Multi-Agent Systems II: Adaptation and Multi-Agent Learning, 2005

How to Learn a Program: Optimal Universal Learners & Goedel Machines.
Proceedings of the Workshop on Approaches and Applications of Inductive Programming, 2005

2004
Self-organizing nets for optimization.
IEEE Trans. Neural Networks, 2004

Optimal Ordered Problem Solver.
Mach. Learn., 2004

A comparison between spiking and differentiable recurrent neural networks on spoken digit recognition.
Proceedings of the IASTED International Conference on Neural Networks and Computational Intelligence, 2004

Hierarchical reinforcement learning with subpolicies specializing for learned subgoals.
Proceedings of the IASTED International Conference on Neural Networks and Computational Intelligence, 2004

Adaptive Online Time Allocation to Search Algorithms.
Proceedings of the Machine Learning: ECML 2004, 2004

Biologically Plausible Speech Recognition with LSTM Neural Nets.
Proceedings of the Biologically Inspired Approaches to Advanced Information Technology, 2004

2003
Kalman filters improve LSTM network performance in problems unsolvable by traditional recurrent nets.
Neural Networks, 2003

Goedel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements
CoRR, 2003

The New AI: General & Sound & Relevant for Physics
CoRR, 2003

A robot that reinforcement-learns to identify and memorize important previous observations.
Proceedings of the 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems, Las Vegas, Nevada, USA, October 27, 2003

2002
Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and LSTM.
Neural Comput., 2002

Learning Precise Timing with LSTM Recurrent Networks.
J. Mach. Learn. Res., 2002

Hierarchies of Generalized Kolmogorov Complexities and Nonenumerable Universal Measures Computable in the Limit.
Int. J. Found. Comput. Sci., 2002

Finding temporal structure in music: blues improvisation with LSTM recurrent networks.
Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing, 2002

Bias-Optimal Incremental Problem Solving.
Proceedings of the Advances in Neural Information Processing Systems 15 [Neural Information Processing Systems, 2002

Reinforcement learning in partially observable mobile robot domains using unsupervised event extraction.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Lausanne, Switzerland, September 30, 2002

Improving Long-Term Online Prediction with Decoupled Extended Kalman Filters.
Proceedings of the Artificial Neural Networks, 2002

Learning Context Sensitive Languages with LSTM Trained with Kalman Filters.
Proceedings of the Artificial Neural Networks, 2002

Learning the Long-Term Structure of the Blues.
Proceedings of the Artificial Neural Networks, 2002

DEKF-LSTM.
Proceedings of the 10th Eurorean Symposium on Artificial Neural Networks, 2002

The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions.
Proceedings of the Computational Learning Theory, 2002

2001
LSTM recurrent networks learn simple context-free and context-sensitive languages.
IEEE Trans. Neural Networks, 2001

Gradient-based Reinforcement Planning in Policy-Search Methods
CoRR, 2001

Optimal Control Using the Transport Equation: The Liouville Machine.
Adapt. Behav., 2001

Sequential Decision Making Based on Direct Search.
Proceedings of the Sequence Learning - Paradigms, Algorithms, and Applications, 2001

Active Learning with Adaptive Grids.
Proceedings of the Artificial Neural Networks, 2001

Market-Based Reinforcement Learning in Partially Observable Worlds.
Proceedings of the Artificial Neural Networks, 2001

Unsupervised Learning in LSTM Recurrent Neural Networks.
Proceedings of the Artificial Neural Networks, 2001

Applying LSTM to Time Series Predictable through Time-Window Approaches.
Proceedings of the Artificial Neural Networks, 2001

2000
Learning to Forget: Continual Prediction with LSTM.
Neural Comput., 2000

Algorithmic Theories of Everything
CoRR, 2000

Neural Processing of Complex Continual Input Streams.
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000

Recurrent Nets that Time and Count.
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000

Evolving strategies for active flow control.
Proceedings of the 2000 Congress on Evolutionary Computation, 2000

1999
Feature Extraction Through LOCOCODE.
Neural Comput., 1999

Reinforcement Learning Soccer Teams with Incomplete World Models.
Auton. Robots, 1999

Nonlinear ICA through low-complexity autoencoders.
Proceedings of the 1999 International Symposium on Circuits and Systems, ISCAS 1999, Orlando, Florida, USA, May 30, 1999

Language identification from prosody without explicit features.
Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Artificial curiosity based on discovering novel algorithmic predictability through coevolution.
Proceedings of the 1999 Congress on Evolutionary Computation, 1999

1998
Fast Online Q(lambda).
Mach. Learn., 1998

Learning Team Strategies: Soccer Case Studies.
Mach. Learn., 1998

Source Separation as a By-Product of Regularization.
Proceedings of the Advances in Neural Information Processing Systems 11, [NIPS Conference, Denver, Colorado, USA, November 30, 1998

Evolving Structured Programs with Hierarchical Instructions and Skip Nodes.
Proceedings of the Fifteenth International Conference on Machine Learning (ICML 1998), 1998

Speeding up Q(lambda)-Learning.
Proceedings of the Machine Learning: ECML-98, 1998

Reinforcement Learning with Self-Modifying Policies.
Proceedings of the Learning to Learn., 1998

1997
Discovering Neural Nets with Low Kolmogorov Complexity and High Generalization Capability.
Neural Networks, 1997

Flat Minima
Neural Comput., 1997

Long Short-Term Memory.
Neural Comput., 1997

Shifting Inductive Bias with Success-Story Algorithm, Adaptive Levin Search, and Incremental Self-Improvement.
Mach. Learn., 1997

Probabilistic Incremental Program Evolution.
Evol. Comput., 1997

HQ-Learning.
Adapt. Behav., 1997

Evolving Soccer Strategies.
Proceedings of the Progress in Connectionist-Based Information Systems: Proceedings of the 1997 International Conference on Neural Information Processing and Intelligent Information Systems, 1997

On Learning Soccer Strategies.
Proceedings of the Artificial Neural Networks, 1997

Unsupervised Coding with LOCOCODE.
Proceedings of the Artificial Neural Networks, 1997

Probabilistic Incremental Program Evolution: Stochastic Search Through Program Space.
Proceedings of the Machine Learning: ECML-97, 1997

A Computer Scientist's View of Life, the Universe, and Everything.
Proceedings of the Foundations of Computer Science: Potential - Theory, 1997

1996
Sequential neural text compression.
IEEE Trans. Neural Networks, 1996

Semilinear Predictability Minimization Produces Well-Known Feature Detectors.
Neural Comput., 1996

LSTM can Solve Hard Long Time Lag Problems.
Proceedings of the Advances in Neural Information Processing Systems 9, 1996

Solving POMDPs with Levin Search and EIRA.
Proceedings of the Machine Learning, 1996

Multi-Agent Learning with the Success-Story Algorithm.
Proceedings of the Distributed Artificial Intelligence Meets Machine Learning, 1996

1995
Discovering Solutions with Low Kolmogorov Complexity and High Generalization Capability.
Proceedings of the Machine Learning, 1995

1994
Predictive Coding with Neural Nets: Application to Text Compression.
Proceedings of the Advances in Neural Information Processing Systems 7, 1994

Simplifying Neural Nets by Discovering Flat Minima.
Proceedings of the Advances in Neural Information Processing Systems 7, 1994

1993
Netzwerkarchitekturen, Zielfunktionen und Kettenregel (Network architectures, objective functions, and chain rule)
, 1993

Discovering Predictable Classifications.
Neural Comput., 1993

A neural network that embeds its own meta-levels.
Proceedings of International Conference on Neural Networks (ICNN'88), San Francisco, CA, USA, March 28, 1993

1992
Learning Factorial Codes by Predictability Minimization.
Neural Comput., 1992

A Fixed Size Storage <i>O</i>(<i>n</i><sup>3</sup>) Time Complexity Learning Algorithm for Fully Recurrent Continually Running Networks.
Neural Comput., 1992

Learning Complex, Extended Sequences Using the Principle of History Compression.
Neural Comput., 1992

1991
An O(n3) learning algorithm for fully recurrent networks
Forschungsberichte, TU Munich, 1991

Adaptive confidence and adaptive curiosity
Forschungsberichte, TU Munich, 1991

Neural sequence chunkers
Forschungsberichte, TU Munich, 1991

Learning to control fast-weight memories: an alternative to dynamic recurrent networks
Forschungsberichte, TU Munich, 1991

Learning to Generate Artificial Fovea Trajectories for Target Detection.
Int. J. Neural Syst., 1991

Learning Unambiguous Reduced Sequence Descriptions.
Proceedings of the Advances in Neural Information Processing Systems 4, 1991

1990
Towards compositional learning with dynamic neural networks
Forschungsberichte, TU Munich, 1990

Learning to generate focus trajectories for attentive vision
Forschungsberichte, TU Munich, 1990

Making the world differentiable: on using self supervised fully recurrent neural networks for dynamic reinforcement learning and planning in non-stationary environments
Forschungsberichte, TU Munich, 1990

Networks adjusting networks
Forschungsberichte, TU Munich, 1990

A local learning algorithm for dynamic feedforward and recurrent networks
Forschungsberichte, TU Munich, 1990

Dynamische neuronale Netze und das fundamentale raumzeitliche Lernproblem.
PhD thesis, 1990

Reinforcement Learning in Markovian and Non-Markovian Environments.
Proceedings of the Advances in Neural Information Processing Systems 3, 1990

An on-line algorithm for dynamic reinforcement learning and planning in reactive environments.
Proceedings of the IJCNN 1990, 1990

1987
Evolutionary principles in self-referential learning, or on learning how to learn: The meta-meta-. hook
PhD thesis, 1987


  Loading...