Search Results for author: Juergen Schmidhuber

Found 21 papers, 7 papers with code

Annotated History of Modern AI and Deep Learning

no code implementations21 Dec 2022 Juergen Schmidhuber

Machine learning is the science of credit assignment: finding patterns in observations that predict the consequences of actions and help to improve future performance.

Deep Learning: Our Miraculous Year 1990-1991

no code implementations12 May 2020 Juergen Schmidhuber

In 2020-2021, we celebrated that many of the basic ideas behind the deep learning revolution were published three decades ago within fewer than 12 months in our "Annus Mirabilis" or "Miraculous Year" 1990-1991 at TU Munich.

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

3 code implementations5 Dec 2019 Juergen Schmidhuber

UDRL generalizes to achieve high rewards or other goals, through input commands such as: get lots of reward within at most so much time!

reinforcement-learning Reinforcement Learning (RL)

Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)

no code implementations11 Jun 2019 Juergen Schmidhuber

I review unsupervised or self-supervised neural networks playing minimax games in game-theoretic settings: (i) Artificial Curiosity (AC, 1990) is based on two such networks.

Investigations on End-to-End Audiovisual Fusion

no code implementations30 Apr 2018 Michael Wand, Ngoc Thang Vu, Juergen Schmidhuber

Audiovisual speech recognition (AVSR) is a method to alleviate the adverse effect of noise in the acoustic signal.

speech-recognition Speech Recognition

One Big Net For Everything

no code implementations24 Feb 2018 Juergen Schmidhuber

Then ONE is retrained in PowerPlay style (2011) on stored input/output traces of (a) ONE's copy executing the new skill and (b) previous instances of ONE whose skills are still considered worth memorizing.

Hindsight policy gradients

1 code implementation ICLR 2019 Paulo Rauber, Avinash Ummadisingu, Filipe Mutz, Juergen Schmidhuber

A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy.

Policy Gradient Methods reinforcement-learning +1

Improving Speaker-Independent Lipreading with Domain-Adversarial Training

no code implementations4 Aug 2017 Michael Wand, Juergen Schmidhuber

We present a Lipreading system, i. e. a speech recognition system using only visual features, which uses domain-adversarial training for speaker independence.

Lipreading speech-recognition +1

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

no code implementations30 Nov 2015 Juergen Schmidhuber

The basic ideas of this report can be applied to many other cases where one RNN-like system exploits the algorithmic information content of another.

Decision Making Reinforcement Learning (RL)

Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation

no code implementations NeurIPS 2015 Marijn F. Stollenga, Wonmin Byeon, Marcus Liwicki, Juergen Schmidhuber

In contrast, Multi-Dimensional Recurrent NNs (MD-RNNs) can perceive the entire spatio-temporal context of each pixel in a few sweeps through all pixels, especially when the RNN is a Long Short-Term Memory (LSTM).

Brain Image Segmentation Image Segmentation +1

Deep Networks with Internal Selective Attention through Feedback Connections

no code implementations NeurIPS 2014 Marijn Stollenga, Jonathan Masci, Faustino Gomez, Juergen Schmidhuber

It harnesses the power of sequential processing to improve classification performance, by allowing the network to iteratively focus its internal attention on some of its convolutional filters.

Deep Attention General Classification

Deep Learning in Neural Networks: An Overview

1 code implementation30 Apr 2014 Juergen Schmidhuber

In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning.

BIG-bench Machine Learning reinforcement-learning +1

Multi-column Deep Neural Networks for Image Classification

1 code implementation13 Feb 2012 Dan Cireşan, Ueli Meier, Juergen Schmidhuber

Traditional methods of computer vision and machine learning cannot match human performance on tasks such as the recognition of handwritten digits or traffic signs.

Classification General Classification +2

Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition

1 code implementation1 Mar 2010 Dan Claudiu Ciresan, Ueli Meier, Luca Maria Gambardella, Juergen Schmidhuber

Good old on-line back-propagation for plain multi-layer perceptrons yields a very low 0. 35% error rate on the famous MNIST handwritten digits benchmark.

Handwritten Digit Recognition

Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes

2 code implementations23 Dec 2008 Juergen Schmidhuber

I argue that data becomes temporarily interesting by itself to some self-improving, but computationally limited, subjective observer once he learns to predict or compress the data in a better way, thus making it subjectively simpler and more beautiful.

Multi-Dimensional Recurrent Neural Networks

4 code implementations14 May 2007 Alex Graves, Santiago Fernandez, Juergen Schmidhuber

Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition.

Handwriting Recognition Image Segmentation +1

New Millennium AI and the Convergence of History

no code implementations19 Jun 2006 Juergen Schmidhuber

Artificial Intelligence (AI) has recently become a real formal science: the new millennium brought the first mathematically sound, asymptotically optimal, universal problem solvers, providing a new, rigorous foundation for the previously largely heuristic field of General AI and embedded agents.

Algorithmic Theories of Everything

no code implementations30 Nov 2000 Juergen Schmidhuber

The probability distribution P from which the history of our universe is sampled represents a theory of everything or TOE.

Inductive Bias Philosophy

A Computer Scientist's View of Life, the Universe, and Everything

no code implementations13 Apr 1999 Juergen Schmidhuber

Is the universe computable?

Quantum Physics Computational Complexity Computers and Society Computational Physics Popular Physics

Cannot find the paper you are looking for? You can Submit a new open access paper.