research
∙
12/21/2022
Annotated History of Modern AI and Deep Learning
Machine learning is the science of credit assignment: finding patterns i...
share
research
∙
05/12/2020
Deep Learning: Our Miraculous Year 1990-1991
In 2020, we will celebrate that many of the basic ideas behind the deep ...
research
∙
12/05/2019
Reinforcement Learning Upside Down: Don't Predict Rewards – Just Map Them to Actions
We transform reinforcement learning (RL) into a form of supervised learn...
research
∙
06/11/2019
Unsupervised Minimax: Adversarial Curiosity, Generative Adversarial Networks, and Predictability Minimization
Generative Adversarial Networks (GANs) learn to model data distributions...
research
∙
04/30/2018
Investigations on End-to-End Audiovisual Fusion
Audiovisual speech recognition (AVSR) is a method to alleviate the adver...
research
∙
02/24/2018
One Big Net For Everything
I apply recent work on "learning to think" (2015) and on PowerPlay (2011...
research
∙
11/16/2017
Hindsight policy gradients
Goal-conditional policies allow reinforcement learning agents to pursue ...
research
∙
08/04/2017
Improving Speaker-Independent Lipreading with Domain-Adversarial Training
We present a Lipreading system, i.e. a speech recognition system using o...
research
∙
11/30/2015
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models
This paper addresses the general problem of reinforcement learning (RL) ...
research
∙
06/24/2015
Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation
Convolutional Neural Networks (CNNs) can be shifted across 2D images or ...
research
∙
07/11/2014
Deep Networks with Internal Selective Attention through Feedback Connections
Traditional convolutional neural networks (CNN) are stationary and feedf...
research
∙
04/30/2014
Deep Learning in Neural Networks: An Overview
In recent years, deep artificial neural networks (including recurrent on...
research
∙
05/02/2013
Testing Hypotheses by Regularized Maximum Mean Discrepancy
Do two data samples come from different distributions? Recent studies of...
research
∙
12/28/2012
A Frequency-Domain Encoding for Neuroevolution
Neuroevolution has yet to scale up to complex reinforcement learning tas...
research
∙
09/29/2012
Self-Delimiting Neural Networks
Self-delimiting (SLIM) programs are a central concept of theoretical com...
research
∙
09/26/2012
Efficient Natural Evolution Strategies
Efficient Natural Evolution Strategies (eNES) is a novel alternative to ...
research
∙
06/18/2012
On the Size of the Online Kernel Sparsification Dictionary
We analyze the size of the dictionary constructed from online kernel spa...
research
∙
02/13/2012
Multi-column Deep Neural Networks for Image Classification
Traditional methods of computer vision and machine learning cannot match...
research
∙
12/31/2011
T-Learning
Traditional Reinforcement Learning (RL) has focused on problems involvin...
research
∙
12/09/2011
Incremental Slow Feature Analysis: Adaptive and Episodic Learning from High-Dimensional Input Streams
Slow Feature Analysis (SFA) extracts features representing the underlyin...
research
∙
06/10/2011
A Linear Time Natural Evolution Strategy for Non-Separable Functions
We present a novel Natural Evolution Strategy (NES) variant, the Rank-On...
research
∙
03/29/2011
Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments
To maximize its success, an AGI typically needs to explore its initially...
research
∙
09/14/2010
Evolution of National Nobel Prize Shares in the 20th Century
We analyze the evolution of cumulative national shares of Nobel Prizes s...
research
∙
03/01/2010
Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition
Good old on-line back-propagation for plain multi-layer perceptrons yiel...
research
∙
12/23/2008
Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, S
I argue that data becomes temporarily interesting by itself to some self...
research
∙
07/09/2008
Algorithm Selection as a Bandit Problem with Unbounded Losses
Algorithm selection is typically based on models of algorithm performanc...
research
∙
04/21/2008
Phoneme recognition in TIMIT with BLSTM-CTC
We compare the performance of a recurrent neural network with the best r...
research
∙
09/05/2007
Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity
I postulate that human or other intelligent agents function or should fu...
research
∙
09/05/2007
Using Data Compressors to Construct Rank Tests
Nonparametric rank tests for homogeneity and component independence are ...
research
∙
08/31/2007
2006: Celebrating 75 years of AI - History and Outlook: the Next 25 Years
When Kurt Goedel layed the foundations of theoretical computer science i...
research
∙
05/14/2007
Multi-Dimensional Recurrent Neural Networks
Recurrent neural networks (RNNs) have proved effective at one dimensiona...
research
∙
06/19/2006
New Millennium AI and the Convergence of History
Artificial Intelligence (AI) has recently become a real formal science: ...
research
∙
03/07/2006
Metric State Space Reinforcement Learning for a Vision-Capable Mobile Robot
We address the problem of autonomously learning controllers for vision-c...
research
∙
12/15/2005
Evolino for recurrent support vector machines
Traditional Support Vector Machines (SVMs) need pre-wired finite time wi...
research
∙
09/25/2003
Goedel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements
We present the first class of mathematically rigorous, general, fully se...
research
∙
02/10/2003
The New AI: General & Sound & Relevant for Physics
Most traditional artificial intelligence (AI) systems of the past 50 yea...
research
∙
07/31/2002
Optimal Ordered Problem Solver
We present a novel, general, optimally fast, incremental way of searchin...
research
∙
11/28/2001
Gradient-based Reinforcement Planning in Policy-Search Methods
We introduce a learning method called "gradient-based reinforcement plan...
research
∙
05/15/2001
Market-Based Reinforcement Learning in Partially Observable Worlds
Unlike traditional reinforcement learning (RL), market-based RL is in pr...
research
∙
11/30/2000
Algorithmic Theories of Everything
The probability distribution P from which the history of our universe is...
research
∙
04/13/1999