Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Juergen Schmidhuber

Juergen Schmidhuber

IDSIA

Deep Learning: Our Miraculous Year 1990-1991


May 12, 2020
Juergen Schmidhuber

* 37 pages, 188 references, based on work of 4 Oct 2019 

  Access Paper or Ask Questions

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


Dec 05, 2019
Juergen Schmidhuber

* 20 pages 

  Access Paper or Ask Questions

Unsupervised Minimax: Adversarial Curiosity, Generative Adversarial Networks, and Predictability Minimization


Jun 11, 2019
Juergen Schmidhuber

* 12 pages, 1 figure, 87 references 

  Access Paper or Ask Questions

Hindsight policy gradients


Feb 20, 2019
Paulo Rauber, Avinash Ummadisingu, Filipe Mutz, Juergen Schmidhuber

* Accepted to ICLR 2019 

  Access Paper or Ask Questions

Investigations on End-to-End Audiovisual Fusion


Apr 30, 2018
Michael Wand, Ngoc Thang Vu, Juergen Schmidhuber

* Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, pages 3041 - 3045 
* Published at ICASSP 2018 

  Access Paper or Ask Questions

One Big Net For Everything


Feb 24, 2018
Juergen Schmidhuber

* 17 pages, 107 references 

  Access Paper or Ask Questions

Improving Speaker-Independent Lipreading with Domain-Adversarial Training


Aug 04, 2017
Michael Wand, Juergen Schmidhuber

* Accepted at Interspeech 2017 

  Access Paper or Ask Questions

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


Nov 30, 2015
Juergen Schmidhuber

* 36 pages, 1 figure. arXiv admin note: substantial text overlap with arXiv:1404.7828 

  Access Paper or Ask Questions

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


Jun 24, 2015
Marijn F. Stollenga, Wonmin Byeon, Marcus Liwicki, Juergen Schmidhuber

* Marijn F. Stollenga and Wonmin Byeon are the shared first authors, both authors contributed equally to this work 

  Access Paper or Ask Questions

Deep Learning in Neural Networks: An Overview


Oct 08, 2014
Juergen Schmidhuber

* Neural Networks, Vol 61, pp 85-117, Jan 2015 
* 88 pages, 888 references 

  Access Paper or Ask Questions

Deep Networks with Internal Selective Attention through Feedback Connections


Jul 28, 2014
Marijn Stollenga, Jonathan Masci, Faustino Gomez, Juergen Schmidhuber

* 13 pages, 3 figures 

  Access Paper or Ask Questions

Testing Hypotheses by Regularized Maximum Mean Discrepancy


May 02, 2013
Somayeh Danafar, Paola M. V. Rancoita, Tobias Glasmachers, Kevin Whittingstall, Juergen Schmidhuber


  Access Paper or Ask Questions

A Frequency-Domain Encoding for Neuroevolution


Dec 28, 2012
Jan Koutník, Juergen Schmidhuber, Faustino Gomez


  Access Paper or Ask Questions

Self-Delimiting Neural Networks


Sep 29, 2012
Juergen Schmidhuber

* 15 pages 

  Access Paper or Ask Questions

Efficient Natural Evolution Strategies


Sep 26, 2012
Yi Sun, Daan Wierstra, Tom Schaul, Juergen Schmidhuber

* Puslished in GECCO'2009 

  Access Paper or Ask Questions

On the Size of the Online Kernel Sparsification Dictionary


Jun 18, 2012
Yi Sun, Faustino Gomez, Juergen Schmidhuber

* ICML2012 

  Access Paper or Ask Questions

Multi-column Deep Neural Networks for Image Classification


Feb 13, 2012
Dan Cireşan, Ueli Meier, Juergen Schmidhuber

* CVPR 2012, p. 3642-3649 
* 20 pages, 14 figures, 8 tables 

  Access Paper or Ask Questions

T-Learning


Dec 31, 2011
Vincent Graziano, Faustino Gomez, Mark Ring, Juergen Schmidhuber


  Access Paper or Ask Questions

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


Dec 09, 2011
Varun Raj Kompella, Matthew Luciw, Juergen Schmidhuber

* Neural Computation, 2012, Vol. 24, No. 11, Pages 2994-3024 

  Access Paper or Ask Questions

A Linear Time Natural Evolution Strategy for Non-Separable Functions


Jun 13, 2011
Yi Sun, Faustino Gomez, Tom Schaul, Juergen Schmidhuber


  Access Paper or Ask Questions

Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments


Mar 29, 2011
Yi Sun, Faustino Gomez, Juergen Schmidhuber


  Access Paper or Ask Questions

Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition


Mar 01, 2010
Dan Claudiu Ciresan, Ueli Meier, Luca Maria Gambardella, Juergen Schmidhuber

* Neural Computation, Volume 22, Number 12, December 2010 
* 14 pages, 2 figures, 4 listings 

  Access Paper or Ask Questions

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


Apr 15, 2009
Juergen Schmidhuber

* Short version: J. Schmidhuber. Simple Algorithmic Theory of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes. Journal of SICE 48(1), 21-32, 2009 
* 35 pages, 3 figures, based on KES 2008 keynote and ALT 2007 / DS 2007 joint invited lecture 

  Access Paper or Ask Questions

Algorithm Selection as a Bandit Problem with Unbounded Losses


Jul 09, 2008
Matteo Gagliolo, Juergen Schmidhuber

* 15 pages, 2 figures 

  Access Paper or Ask Questions

Phoneme recognition in TIMIT with BLSTM-CTC


Apr 21, 2008
Santiago Fernández, Alex Graves, Juergen Schmidhuber

* 8 pages 

  Access Paper or Ask Questions

Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity


Sep 05, 2007
Juergen Schmidhuber

* 15 pages, 3 highly compressible low-complexity drawings. Joint Invited Lecture for Algorithmic Learning Theory (ALT 2007) and Discovery Science (DS 2007), Sendai, Japan, 2007 

  Access Paper or Ask Questions

2006: Celebrating 75 years of AI - History and Outlook: the Next 25 Years


Aug 31, 2007
Juergen Schmidhuber

* 14 pages; preprint of invited contribution to the Proceedings of the ``50th Anniversary Summit of Artificial Intelligence'' at Monte Verita, Ascona, Switzerland, 9-14 July 2006 

  Access Paper or Ask Questions

Multi-Dimensional Recurrent Neural Networks


May 14, 2007
Alex Graves, Santiago Fernandez, Juergen Schmidhuber

* 10 pages, 10 figures 

  Access Paper or Ask Questions

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


Dec 17, 2006
Juergen Schmidhuber

* Variants published in "Adaptive Agents and Multi-Agent Systems II", LNCS 3394, p. 1-23, Springer, 2005: ISBN 978-3-540-25260-3; as well as in Proc. ICANN 2005, LNCS 3697, p. 223-233, Springer, 2005 (plenary talk); as well as in "Artificial General Intelligence", Series: Cognitive Technologies, Springer, 2006: ISBN-13: 978-3-540-23733-4 
* 29 pages, 1 figure, minor improvements, updated references 

  Access Paper or Ask Questions