Difference between revisions of "Jürgen Schmidhuber"
GerdIsenberg (talk | contribs) (Created page with "'''Home * People * Jürgen Schmidhuber''' FILE:JuergenSchmidhuber.jpg|border|right|thumb|link=https://nnaisense.com/| Jürgen Schmidhuber <ref>[https://nn...") |
GerdIsenberg (talk | contribs) |
||
(4 intermediate revisions by the same user not shown) | |||
Line 4: | Line 4: | ||
'''Jürgen H. Schmidhuber''',<br/> | '''Jürgen H. Schmidhuber''',<br/> | ||
− | a German computer scientist, researcher and entrepreneur in the field of [[Artificial Intelligence|artificial intelligence]], in 2014 co-founder and subsequently chief scientist of the AI company ''NNAISENSE'' <ref>[https://nnaisense.com/ NNAISENSE Team]</ref>. His further affiliations include the Faculty of Computer Science, [https://en.wikipedia.org/wiki/Universit%C3%A0_della_Svizzera_italiana University of Lugano], | + | a German computer scientist, researcher and entrepreneur in the field of [[Artificial Intelligence|artificial intelligence]], in 2014 co-founder and subsequently chief scientist of the AI company ''NNAISENSE'' <ref>[https://nnaisense.com/ NNAISENSE Team]</ref>. His further academic and commercial affiliations include the Faculty of Computer Science, [https://en.wikipedia.org/wiki/Universit%C3%A0_della_Svizzera_italiana University of Lugano], |
[https://en.wikipedia.org/wiki/SUPSI SUPSI] in [https://en.wikipedia.org/wiki/Manno Manno], | [https://en.wikipedia.org/wiki/SUPSI SUPSI] in [https://en.wikipedia.org/wiki/Manno Manno], | ||
− | + | the Swiss [https://en.wikipedia.org/wiki/IDSIA AI Lab IDSIA], [https://en.wikipedia.org/wiki/Lugano Lugano], | |
and, as student, docent, and from 2004 until 2009 as [https://en.wikipedia.org/wiki/Professor#Main_positions_2 Professor Extraordinarius], the [[Technical University of Munich]]. | and, as student, docent, and from 2004 until 2009 as [https://en.wikipedia.org/wiki/Professor#Main_positions_2 Professor Extraordinarius], the [[Technical University of Munich]]. | ||
Line 18: | Line 18: | ||
==1990 ...== | ==1990 ...== | ||
* [[Jürgen Schmidhuber]] ('''1990'''). ''Reinforcement Learning in Markovian and Non-Markovian Environments''. [https://dblp.uni-trier.de/db/conf/nips/nips1990.html NIPS 1990], [ftp://ftp.idsia.ch/pub/juergen/nipsnonmarkov.pdf pdf] | * [[Jürgen Schmidhuber]] ('''1990'''). ''Reinforcement Learning in Markovian and Non-Markovian Environments''. [https://dblp.uni-trier.de/db/conf/nips/nips1990.html NIPS 1990], [ftp://ftp.idsia.ch/pub/juergen/nipsnonmarkov.pdf pdf] | ||
− | * [[Jürgen Schmidhuber]], [[Rudolf Huber]] ('''1991'''). ''[https://www. | + | * [[Jürgen Schmidhuber]], [[Rudolf Huber]] ('''1991'''). ''[https://www.researchgate.net/publication/2290900_Using_Adaptive_Sequential_Neurocontrol_For_Efficient_Learning_Of_Translation_And_Rotation_Invariance Using sequential adaptive Neuro-control for efficient Learning of Rotation and Translation Invariance]''. In [[Mathematician#TKohonen|Teuvo Kohonen]], [https://dblp.uni-trier.de/pers/hd/m/Makisara:Kai Kai Mäkisara], [http://users.ics.tkk.fi/ollis/ Olli Simula], [http://cis.legacy.ics.tkk.fi/jari/ Jari Kangas] (eds.) ('''1991'''). ''[https://www.sciencedirect.com/book/9780444891785/artificial-neural-networks#book-description Artificial Neural Networks]''. [https://en.wikipedia.org/wiki/Elsevier Elsevier] |
* [[Jürgen Schmidhuber]] ('''1991'''). ''[http://people.idsia.ch/~juergen/promotion/ Dynamische neuronale Netze und das fundamentale raumzeitliche Lernproblem]'' (Dynamic Neural Nets and the Fundamental Spatio-Temporal Credit Assignment Problem). Ph.D. thesis | * [[Jürgen Schmidhuber]] ('''1991'''). ''[http://people.idsia.ch/~juergen/promotion/ Dynamische neuronale Netze und das fundamentale raumzeitliche Lernproblem]'' (Dynamic Neural Nets and the Fundamental Spatio-Temporal Credit Assignment Problem). Ph.D. thesis | ||
* [[Jürgen Schmidhuber]] ('''1993'''). ''[http://www.idsia.ch/~juergen/habilitation/habilitation.html Netzwerkarchitekturen, Zielfunktionen und Kettenregel]''. Habilitationsschrift, [[Technical University of Munich|Technische Universität München]] (German) | * [[Jürgen Schmidhuber]] ('''1993'''). ''[http://www.idsia.ch/~juergen/habilitation/habilitation.html Netzwerkarchitekturen, Zielfunktionen und Kettenregel]''. Habilitationsschrift, [[Technical University of Munich|Technische Universität München]] (German) | ||
Line 24: | Line 24: | ||
* [[Mathematician#SHochreiter|Sepp Hochreiter]], [[Jürgen Schmidhuber]] ('''1997'''). ''Long short-term memory''. [https://en.wikipedia.org/wiki/Neural_Computation_%28journal%29 Neural Computation], Vol. 9, No. 8, [http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf pdf] | * [[Mathematician#SHochreiter|Sepp Hochreiter]], [[Jürgen Schmidhuber]] ('''1997'''). ''Long short-term memory''. [https://en.wikipedia.org/wiki/Neural_Computation_%28journal%29 Neural Computation], Vol. 9, No. 8, [http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf pdf] | ||
* [[Jürgen Schmidhuber]] ('''1997'''). ''[http://people.idsia.ch/~juergen/locoart/locoart.html Low-Complexity Art]''. [https://en.wikipedia.org/wiki/Leonardo_%28journal%29 Leonardo, Journal of the International Society for the Arts, Sciences, and Technology], Vol. 30 No. 2, [https://en.wikipedia.org/wiki/MIT_Press MIT Press] | * [[Jürgen Schmidhuber]] ('''1997'''). ''[http://people.idsia.ch/~juergen/locoart/locoart.html Low-Complexity Art]''. [https://en.wikipedia.org/wiki/Leonardo_%28journal%29 Leonardo, Journal of the International Society for the Arts, Sciences, and Technology], Vol. 30 No. 2, [https://en.wikipedia.org/wiki/MIT_Press MIT Press] | ||
− | * [[Marco Wiering]], [[Jürgen Schmidhuber]] ('''1997'''). ''[ | + | * [[Marco Wiering]], [[Jürgen Schmidhuber]] ('''1997'''). ''[http://people.idsia.ch/~juergen/hq/ab.html HQ-learning]''. [https://en.wikipedia.org/wiki/Adaptive_Behavior_%28journal%29 Adaptive Behavior], Vol. 6, No 2 |
− | * [[Marco Wiering]], [[Jürgen Schmidhuber]] ('''1998'''). ''[https:// | + | * [[Marco Wiering]], [[Jürgen Schmidhuber]] ('''1998'''). ''[https://link.springer.com/article/10.1023/A:1007562800292 Fast online Q (λ)]''. [https://en.wikipedia.org/wiki/Machine_Learning_%28journal%29 Machine Learning], Vol. 33, No. 1 |
==2000 ...== | ==2000 ...== | ||
* [http://dblp.uni-trier.de/pers/hd/k/Klapper=Rybicka:Magdalena Magdalena Klapper-Rybicka], [[Nicol N. Schraudolph]], [[Jürgen Schmidhuber]] ('''2001'''). ''[http://nic.schraudolph.org/bib2html/b2hd-KlaSchSch01.html Unsupervised Learning in LSTM Recurrent Neural Networks]''. [http://dblp.uni-trier.de/db/conf/icann/icann2001.html#Klapper-RybickaSS01 ICANN 2001] | * [http://dblp.uni-trier.de/pers/hd/k/Klapper=Rybicka:Magdalena Magdalena Klapper-Rybicka], [[Nicol N. Schraudolph]], [[Jürgen Schmidhuber]] ('''2001'''). ''[http://nic.schraudolph.org/bib2html/b2hd-KlaSchSch01.html Unsupervised Learning in LSTM Recurrent Neural Networks]''. [http://dblp.uni-trier.de/db/conf/icann/icann2001.html#Klapper-RybickaSS01 ICANN 2001] | ||
Line 40: | Line 40: | ||
* [[Jürgen Schmidhuber]] ('''2015'''). ''[http://people.idsia.ch/~juergen/deep-learning-overview.html Deep Learning in Neural Networks: An Overview]''. [https://en.wikipedia.org/wiki/Neural_Networks_(journal) Neural Networks], Vol. 61 | * [[Jürgen Schmidhuber]] ('''2015'''). ''[http://people.idsia.ch/~juergen/deep-learning-overview.html Deep Learning in Neural Networks: An Overview]''. [https://en.wikipedia.org/wiki/Neural_Networks_(journal) Neural Networks], Vol. 61 | ||
* [[Jürgen Schmidhuber]] ('''2015'''). ''On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models''. [https://arxiv.org/abs/1511.09249 arXiv:1511.09249] | * [[Jürgen Schmidhuber]] ('''2015'''). ''On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models''. [https://arxiv.org/abs/1511.09249 arXiv:1511.09249] | ||
+ | * [https://scholar.google.com/citations?user=52L53fEAAAAJ&hl=en Marijn F. Stollenga], [[Alan J. Lockett]], [[Jürgen Schmidhuber]] ('''2015'''). ''[https://ieeexplore.ieee.org/abstract/document/7363550 The Natural Gradient as a control signal for a humanoid robot]''. [https://dblp.uni-trier.de/db/conf/humanoids/humanoids2015.html Humanoids 2015] | ||
* [[Jürgen Schmidhuber]] ('''2018'''). ''One Big Net For Everything''. [https://arxiv.org/abs/1802.08864 arXiv:1802.08864] | * [[Jürgen Schmidhuber]] ('''2018'''). ''One Big Net For Everything''. [https://arxiv.org/abs/1802.08864 arXiv:1802.08864] | ||
Latest revision as of 20:26, 13 July 2020
Home * People * Jürgen Schmidhuber
Jürgen H. Schmidhuber,
a German computer scientist, researcher and entrepreneur in the field of artificial intelligence, in 2014 co-founder and subsequently chief scientist of the AI company NNAISENSE [2]. His further academic and commercial affiliations include the Faculty of Computer Science, University of Lugano,
SUPSI in Manno,
the Swiss AI Lab IDSIA, Lugano,
and, as student, docent, and from 2004 until 2009 as Professor Extraordinarius, the Technical University of Munich.
Jürgen Schmidhuber is known for his research on machine learning, genetic programming, universal AI along with his former postdoc Marcus Hutter, artificial neural networks in particular recurrent neural networks (RNN) and deep learning, where he along with Sepp Hochreiter coined the term long short-term memory [3], Zuse's calculating space, Gödel machines, universal search, theory of everything, digital physics, algorithmic information theory, Kolmogorov complexity, and low-complexity art [4] .
Contents
See also
Selected Publications
1990 ...
- Jürgen Schmidhuber (1990). Reinforcement Learning in Markovian and Non-Markovian Environments. NIPS 1990, pdf
- Jürgen Schmidhuber, Rudolf Huber (1991). Using sequential adaptive Neuro-control for efficient Learning of Rotation and Translation Invariance. In Teuvo Kohonen, Kai Mäkisara, Olli Simula, Jari Kangas (eds.) (1991). Artificial Neural Networks. Elsevier
- Jürgen Schmidhuber (1991). Dynamische neuronale Netze und das fundamentale raumzeitliche Lernproblem (Dynamic Neural Nets and the Fundamental Spatio-Temporal Credit Assignment Problem). Ph.D. thesis
- Jürgen Schmidhuber (1993). Netzwerkarchitekturen, Zielfunktionen und Kettenregel. Habilitationsschrift, Technische Universität München (German)
- Sepp Hochreiter, Jürgen Schmidhuber (1995). Simplifying Neural Nets by Discovering Flat Minima. In Gerald Tesauro, David S. Touretzky and Todd K. Leen (eds.), Advances in Neural Information Processing Systems 7, NIPS'7, pages 529-536. MIT Press
- Sepp Hochreiter, Jürgen Schmidhuber (1997). Long short-term memory. Neural Computation, Vol. 9, No. 8, pdf
- Jürgen Schmidhuber (1997). Low-Complexity Art. Leonardo, Journal of the International Society for the Arts, Sciences, and Technology, Vol. 30 No. 2, MIT Press
- Marco Wiering, Jürgen Schmidhuber (1997). HQ-learning. Adaptive Behavior, Vol. 6, No 2
- Marco Wiering, Jürgen Schmidhuber (1998). Fast online Q (λ). Machine Learning, Vol. 33, No. 1
2000 ...
- Magdalena Klapper-Rybicka, Nicol N. Schraudolph, Jürgen Schmidhuber (2001). Unsupervised Learning in LSTM Recurrent Neural Networks. ICANN 2001
- Jürgen Schmidhuber (2003). The New AI:General & Sound & Relevant for Physics. Technical Report IDSIA-04-03
- Jürgen Schmidhuber (2004). Turing's impact. Nature 429
- Faustino J. Gomez, Jürgen Schmidhuber (2005). Co-Evolving Recurrent Neurons Learn Deep Memory POMDPs. GECCO 2005, pdf
- Jürgen Schmidhuber (2007). 2006: Celebrating 75 years of AI - History and Outlook: the Next 25 Years. arXiv:0708.4311
- Jürgen Schmidhuber (2007). Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity. arXiv:0709.0674
- Jürgen Schmidhuber (2009). Ultimate Cognition à la Gödel. Cognitive Computation, Vol. 1, No. 2, pdf
2010 ...
- Jürgen Schmidhuber (2010). Formal Theory of Fun and Creativity. ECML/PKDD, pdf
- Jürgen Schmidhuber (2013). My First Deep Learning System of 1991 + Deep Learning Timeline 1962-2013. arXiv:1312.5548
- Jürgen Schmidhuber (2014). Deep Learning in Neural Networks: An Overview. arXiv:1404.7828
- Jürgen Schmidhuber (2015). Deep Learning in Neural Networks: An Overview. Neural Networks, Vol. 61
- Jürgen Schmidhuber (2015). On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models. arXiv:1511.09249
- Marijn F. Stollenga, Alan J. Lockett, Jürgen Schmidhuber (2015). The Natural Gradient as a control signal for a humanoid robot. Humanoids 2015
- Jürgen Schmidhuber (2018). One Big Net For Everything. arXiv:1802.08864
External Links
- Jürgen Schmidhuber from Wikipedia
- Jürgen Schmidhuber - The Mathematics Genealogy Project
- Juergen Schmidhuber - Google Scholar Citations
- Deep Learning - Scholarpedia by Jürgen Schmidhuber
- Build An Optimal Scientist, Then Retire, Jürgen Schmidhuber Interview at h+ Magazine by Michael Anissimov, January 5, 2010
Schmidhuber Links
- Juergen Schmidhuber's home page
- Learning Robots/ Robot Learning
- Reinforcement Learning and POMDPs [7]
- Universal Learning Machines - Optimal Universal AI
- Very Deep Learning Since 1991
- Neural Nets for Finance
- Kurt Gödel by Jürgen Schmidhuber
- Femme Fractale: Lady in Red (1997-2010)
- Formal Theory of Creativity and Fun and Intrinsic Motivation Explains Science, Art, Music, Humor
- Videos of Juergen Schmidhuber & the Swiss AI Lab IDSIA