25,161
edits
Changes
Created page with "'''Home * People * Nicol N. Schraudolph''' FILE:Nicol_Schraudolph.jpg|border|right|thumb|link=http://canberra06.mlss.cc/index.html%3Fq=user%252Fview%252F1..."
'''[[Main Page|Home]] * [[People]] * Nicol N. Schraudolph'''
[[FILE:Nicol_Schraudolph.jpg|border|right|thumb|link=http://canberra06.mlss.cc/index.html%3Fq=user%252Fview%252F13.html| Nic Schraudolph <ref>[http://canberra06.mlss.cc/index.html%3Fq=user%252Fview%252F13.html Nic Schraudolph - NICTA]</ref> ]]
'''Nicol N. (Nic) Schraudolph''',<br/>
a German computer scientist, independent researcher and consultant in [[Learning|machine learning]] and [https://en.wikipedia.org/wiki/Mathematical_optimization optimization], in particular [https://en.wikipedia.org/wiki/Stochastic_gradient_descent stochastic gradient descent].
He received a B.Sc. degree in computer science (CS) from the [https://en.wikipedia.org/wiki/University_of_Essex University of Essex] in 1988, and a M.Sc. and Ph.D. degrees in computer science and cognitive science from [https://en.wikipedia.org/wiki/University_of_California,_San_Diego University of California, San Diego], the Ph.D. in 1995 on optimization of [https://en.wikipedia.org/wiki/Entropy_%28information_theory%29 entropy] with [[Neural Networks|neural networks]] under [[Terrence J. Sejnowski]]
<ref>[[Nicol N. Schraudolph]] ('''1995'''). ''[https://nic.schraudolph.org/bib2html/b2hd-Schraudolph95 Optimization of Entropy with Neural Networks]''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_California,_San_Diego University of California, San Diego]</ref>.
His previous research affiliations include [https://en.wikipedia.org/wiki/NICTA NICTA] [https://de.wikipedia.org/wiki/Canberra] Canberra], [[ETH Zurich]] and [https://en.wikipedia.org/wiki/Dalle_Molle_Institute_for_Artificial_Intelligence_Research Dalle Molle Institute for Artificial Intelligence Research], [https://en.wikipedia.org/wiki/Lugano_District Lugano].
=Learning Go=
Along with [[Peter Dayan]] and his advisor, [[Terrence J. Sejnowski]], Nicol Schraudolph applied [[Temporal Difference Learning|temporal difference learning]] to an [[Evaluation|evaluation function]] in the game of [[Go]], as published in 1994 <ref>[[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''1994'''). ''[https://nic.schraudolph.org/bib2html/b2hd-SchDaySej94.html Temporal Difference Learning of Position Evaluation in the Game of Go]''. [http://papers.nips.cc/book/advances-in-neural-information-processing-systems-6-1993 Advances in Neural Information Processing Systems 6]</ref>, and in 2001 <ref>[[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''2001'''). ''[http://nic.schraudolph.org/bib2html/b2hd-SchDaySej01.html Learning to Evaluate Go Positions via Temporal Difference Methods]''. in [[Norio Baba]], [[Lakhmi C. Jain]] (eds.) ('''2001'''). ''[http://jasss.soc.surrey.ac.uk/7/1/reviews/takama.html Computational Intelligence in Games, Studies in Fuzziness and Soft Computing]''. [http://www.springer.com/economics?SGWID=1-165-6-73481-0 Physica-Verlag]</ref>.
[[FILE:gotemporaldiffeval.jpg|none|border|text-bottom|543px|link=http://nic.schraudolph.org/bib2html/b2hd-SchDaySej94.html]]
A modular network architecture that takes advantage of board symmetries,<br/>
translation invariance and localized reinforcement to evaluate Go positions <ref>Image 1 from [[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''1994'''). ''[https://nic.schraudolph.org/bib2html/b2hd-SchDaySej94.html Temporal Difference Learning of Position Evaluation in the Game of Go]''. [http://papers.nips.cc/book/advances-in-neural-information-processing-systems-6-1993 Advances in Neural Information Processing Systems 6]</ref>
=Selected Publications=
<ref>[https://dblp.uni-trier.de/pers/hd/s/Schraudolph:Nicol_N= dblp: Nicol N. Schraudolph]</ref> <ref>[https://dblp.uni-trier.de/pers/hd/s/Schraudolph:Nic dblp: Nic Schraudolph]</ref> <ref>[https://nic.schraudolph.org/bib2html/sort_date.html Nic Schraudolphs's Publications by Year]</ref>
==1991 ...==
* [[Nicol N. Schraudolph]], [[Terrence J. Sejnowski]] ('''1991'''). ''[https://papers.nips.cc/paper/472-competitive-anti-hebbian-learning-of-invariants Competitive Anti-Hebbian Learning of Invariants]''. [https://papers.nips.cc/book/advances-in-neural-information-processing-systems-4-1991 NIPS 1991]
* [[Nicol N. Schraudolph]], [[Terrence J. Sejnowski]] ('''1992'''). ''[https://papers.nips.cc/paper/628-unsupervised-discrimination-of-clustered-data-via-optimization-of-binary-information-gain Unsupervised Discrimination of Clustered Data via Optimization of Binary Information Gain]''. [https://papers.nips.cc/book/advances-in-neural-information-processing-systems-5-1992 NIPS 1992]
* <span id="1993"></span>[[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''1993'''). ''[https://papers.nips.cc/paper/820-temporal-difference-learning-of-position-evaluation-in-the-game-of-go Temporal Difference Learning of Position Evaluation in the Game of Go]''. [https://papers.nips.cc/book/advances-in-neural-information-processing-systems-6-1993 NIPS 1993] <ref>[http://satirist.org/learn-game/systems/go-net.html Nici Schraudolph’s go networks], review by [[Jay Scott]]</ref>
* [[Nicol N. Schraudolph]], [[Terrence J. Sejnowski]] ('''1994'''). ''[https://papers.nips.cc/paper/1003-plasticity-mediated-competitive-learning Plasticity-Mediated Competitive Learning]''. [https://papers.nips.cc/book/advances-in-neural-information-processing-systems-7-1994 NIPS 1994]
* [[Nicol N. Schraudolph]] ('''1995'''). ''[https://nic.schraudolph.org/bib2html/b2hd-Schraudolph95 Optimization of Entropy with Neural Networks]''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_California,_San_Diego University of California, San Diego]
* [[Nicol N. Schraudolph]], [[Terrence J. Sejnowski]] ('''1996'''). ''[https://nic.schraudolph.org/bib2html/b2hd-SchSej96.html Tempering Backpropagation Networks: Not All Weights are Created Equal]''. [https://papers.nips.cc/book/advances-in-neural-information-processing-systems-8-1995 NIPS 1995], [https://papers.nips.cc/paper/1100-tempering-backpropagation-networks-not-all-weights-are-created-equal.pdf pdf]
* [[Nicol N. Schraudolph]] ('''1998'''). ''[https://nic.schraudolph.org/bib2html/b2hd-Schraudolph98.html Centering Neural Network Gradient Factors]''. Neural Networks: Tricks of the Trade, 2nd ed. 2012
==2000 ...==
* [[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''2001'''). ''[https://nic.schraudolph.org/bib2html/b2hd-SchDaySej01.html Learning to Evaluate Go Positions via Temporal Difference Methods]''. [http://jasss.soc.surrey.ac.uk/7/1/reviews/takama.html Computational Intelligence in Games, Studies in Fuzziness and Soft Computing]. [https://www.springer.com/economics?SGWID=0-165-6-73479-0 Physica-Verlag], revised version of [[#1993|1993 paper]]
* [https://dblp.uni-trier.de/pers/hd/k/Klapper=Rybicka:Magdalena Magdalena Klapper-Rybicka], [[Nicol N. Schraudolph]], [[Jürgen Schmidhuber]] ('''2001'''). ''[https://nic.schraudolph.org/bib2html/b2hd-KlaSchSch01.html Unsupervised Learning in LSTM Recurrent Neural Networks]''. [https://dblp.uni-trier.de/db/conf/icann/icann2001.html ICANN 2001]
* [https://dblp.uni-trier.de/pers/hd/c/Chik:Desmond Desmond Chik], [https://dblp.uni-trier.de/pers/hd/t/Trumpf:Jochen Jochen Trumpf], [[Nicol N. Schraudolph]] ('''2007'''). ''[https://nic.schraudolph.org/bib2html/b2hd-ChiTruSch07.html 3D Hand Tracking in a Stochastic Approximation Setting]''. [https://dblp.uni-trier.de/db/conf/humo/humo2007.html Workshop on Human Motion 2007]
* [https://scholar.google.com/citations?user=tqcSvFIAAAAJ&hl=en S.V.N. Vishwanathan], [[Mathematician#KBorgwardt|Karsten Borgwardt]], [https://dblp.uni-trier.de/pers/hd/k/Kondor:Risi Risi Kondor], [[Nicol N. Schraudolph]] ('''2008'''). ''Graph Kernels''. [https://arxiv.org/abs/0807.0093 arXiv:0807.0093] <ref>[https://en.wikipedia.org/wiki/Graph_kernel Graph kernel from Wikipedia]</ref>
* [[Nicol N. Schraudolph]], [https://scholar.google.com.au/citations?user=8sq16RkAAAAJ&hl=en Dmitry Kamenetsky] ('''2008'''). ''Efficient Exact Inference in Planar Ising Models''. [https://arxiv.org/abs/0810.4401 arXiv:0810.4401]
==2010 ...==
* [https://scholar.google.com/citations?user=tqcSvFIAAAAJ&hl=en S.V.N. Vishwanathan], [[Nicol N. Schraudolph]], [https://dblp.uni-trier.de/pers/hd/k/Kondor:Risi Risi Kondor], [[Mathematician#KBorgwardt|Karsten Borgwardt]] ('''2010'''). ''[http://jmlr.csail.mit.edu/papers/v11/vishwanathan10a.html Graph Kernels]''. [https://de.wikipedia.org/wiki/Journal_of_Machine_Learning_Research Journal of Machine Learning Research], Vol. 11
* [[Nicol N. Schraudolph]] ('''2010'''). ''Polynomial-Time Exact Inference in NP-HardBinary MRFs via Reweighted Perfect Matching''. [https://dblp.uni-trier.de/db/journals/jmlr/jmlrp9.html AISTATS 2010], [http://proceedings.mlr.press/v9/schraudolph10a/schraudolph10a.pdf pdf]
* [[Nicol N. Schraudolph]] ('''2012'''). ''[https://link.springer.com/chapter/10.1007/978-3-642-35289-8_14 Centering Neural Network Gradient Factors]''. [https://link.springer.com/book/10.1007%2F978-3-642-35289-8 Neural Networks: Tricks of the Trade], 2nd edition
* [[Nicol N. Schraudolph]] ('''201?'''). ''Rapid Stochastic Gradient Descentfor Atomic Learning''. [https://en.wikipedia.org/wiki/NICTA NICTA], [https://www.yumpu.com/en/document/view/10166827/slides-machine-learning-theory slides] [http://hunch.net/~jl/conferences/atomic_learning/Nic.pdf as pdf], [http://canberra06.mlss.cc/slides/Nic-Schraudolph.pdf pdf]
=External Links=
* [https://nic.schraudolph.org/ Nic Schraudolph]
* [https://nic.schraudolph.org/teach/NNcourse/ Introduction to Neural Networks] by [[Nicol N. Schraudolph]] and [https://scholar.google.com/citations?user=E-vg2zQAAAAJ&hl=en Fred Cummins]
* [https://nic.schraudolph.org/teach/opengo.html Going for Go]
=References=
<references />
'''[[People|Up one level]]'''
[[Category:Researcher|Schraudolph]]
[[FILE:Nicol_Schraudolph.jpg|border|right|thumb|link=http://canberra06.mlss.cc/index.html%3Fq=user%252Fview%252F13.html| Nic Schraudolph <ref>[http://canberra06.mlss.cc/index.html%3Fq=user%252Fview%252F13.html Nic Schraudolph - NICTA]</ref> ]]
'''Nicol N. (Nic) Schraudolph''',<br/>
a German computer scientist, independent researcher and consultant in [[Learning|machine learning]] and [https://en.wikipedia.org/wiki/Mathematical_optimization optimization], in particular [https://en.wikipedia.org/wiki/Stochastic_gradient_descent stochastic gradient descent].
He received a B.Sc. degree in computer science (CS) from the [https://en.wikipedia.org/wiki/University_of_Essex University of Essex] in 1988, and a M.Sc. and Ph.D. degrees in computer science and cognitive science from [https://en.wikipedia.org/wiki/University_of_California,_San_Diego University of California, San Diego], the Ph.D. in 1995 on optimization of [https://en.wikipedia.org/wiki/Entropy_%28information_theory%29 entropy] with [[Neural Networks|neural networks]] under [[Terrence J. Sejnowski]]
<ref>[[Nicol N. Schraudolph]] ('''1995'''). ''[https://nic.schraudolph.org/bib2html/b2hd-Schraudolph95 Optimization of Entropy with Neural Networks]''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_California,_San_Diego University of California, San Diego]</ref>.
His previous research affiliations include [https://en.wikipedia.org/wiki/NICTA NICTA] [https://de.wikipedia.org/wiki/Canberra] Canberra], [[ETH Zurich]] and [https://en.wikipedia.org/wiki/Dalle_Molle_Institute_for_Artificial_Intelligence_Research Dalle Molle Institute for Artificial Intelligence Research], [https://en.wikipedia.org/wiki/Lugano_District Lugano].
=Learning Go=
Along with [[Peter Dayan]] and his advisor, [[Terrence J. Sejnowski]], Nicol Schraudolph applied [[Temporal Difference Learning|temporal difference learning]] to an [[Evaluation|evaluation function]] in the game of [[Go]], as published in 1994 <ref>[[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''1994'''). ''[https://nic.schraudolph.org/bib2html/b2hd-SchDaySej94.html Temporal Difference Learning of Position Evaluation in the Game of Go]''. [http://papers.nips.cc/book/advances-in-neural-information-processing-systems-6-1993 Advances in Neural Information Processing Systems 6]</ref>, and in 2001 <ref>[[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''2001'''). ''[http://nic.schraudolph.org/bib2html/b2hd-SchDaySej01.html Learning to Evaluate Go Positions via Temporal Difference Methods]''. in [[Norio Baba]], [[Lakhmi C. Jain]] (eds.) ('''2001'''). ''[http://jasss.soc.surrey.ac.uk/7/1/reviews/takama.html Computational Intelligence in Games, Studies in Fuzziness and Soft Computing]''. [http://www.springer.com/economics?SGWID=1-165-6-73481-0 Physica-Verlag]</ref>.
[[FILE:gotemporaldiffeval.jpg|none|border|text-bottom|543px|link=http://nic.schraudolph.org/bib2html/b2hd-SchDaySej94.html]]
A modular network architecture that takes advantage of board symmetries,<br/>
translation invariance and localized reinforcement to evaluate Go positions <ref>Image 1 from [[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''1994'''). ''[https://nic.schraudolph.org/bib2html/b2hd-SchDaySej94.html Temporal Difference Learning of Position Evaluation in the Game of Go]''. [http://papers.nips.cc/book/advances-in-neural-information-processing-systems-6-1993 Advances in Neural Information Processing Systems 6]</ref>
=Selected Publications=
<ref>[https://dblp.uni-trier.de/pers/hd/s/Schraudolph:Nicol_N= dblp: Nicol N. Schraudolph]</ref> <ref>[https://dblp.uni-trier.de/pers/hd/s/Schraudolph:Nic dblp: Nic Schraudolph]</ref> <ref>[https://nic.schraudolph.org/bib2html/sort_date.html Nic Schraudolphs's Publications by Year]</ref>
==1991 ...==
* [[Nicol N. Schraudolph]], [[Terrence J. Sejnowski]] ('''1991'''). ''[https://papers.nips.cc/paper/472-competitive-anti-hebbian-learning-of-invariants Competitive Anti-Hebbian Learning of Invariants]''. [https://papers.nips.cc/book/advances-in-neural-information-processing-systems-4-1991 NIPS 1991]
* [[Nicol N. Schraudolph]], [[Terrence J. Sejnowski]] ('''1992'''). ''[https://papers.nips.cc/paper/628-unsupervised-discrimination-of-clustered-data-via-optimization-of-binary-information-gain Unsupervised Discrimination of Clustered Data via Optimization of Binary Information Gain]''. [https://papers.nips.cc/book/advances-in-neural-information-processing-systems-5-1992 NIPS 1992]
* <span id="1993"></span>[[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''1993'''). ''[https://papers.nips.cc/paper/820-temporal-difference-learning-of-position-evaluation-in-the-game-of-go Temporal Difference Learning of Position Evaluation in the Game of Go]''. [https://papers.nips.cc/book/advances-in-neural-information-processing-systems-6-1993 NIPS 1993] <ref>[http://satirist.org/learn-game/systems/go-net.html Nici Schraudolph’s go networks], review by [[Jay Scott]]</ref>
* [[Nicol N. Schraudolph]], [[Terrence J. Sejnowski]] ('''1994'''). ''[https://papers.nips.cc/paper/1003-plasticity-mediated-competitive-learning Plasticity-Mediated Competitive Learning]''. [https://papers.nips.cc/book/advances-in-neural-information-processing-systems-7-1994 NIPS 1994]
* [[Nicol N. Schraudolph]] ('''1995'''). ''[https://nic.schraudolph.org/bib2html/b2hd-Schraudolph95 Optimization of Entropy with Neural Networks]''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_California,_San_Diego University of California, San Diego]
* [[Nicol N. Schraudolph]], [[Terrence J. Sejnowski]] ('''1996'''). ''[https://nic.schraudolph.org/bib2html/b2hd-SchSej96.html Tempering Backpropagation Networks: Not All Weights are Created Equal]''. [https://papers.nips.cc/book/advances-in-neural-information-processing-systems-8-1995 NIPS 1995], [https://papers.nips.cc/paper/1100-tempering-backpropagation-networks-not-all-weights-are-created-equal.pdf pdf]
* [[Nicol N. Schraudolph]] ('''1998'''). ''[https://nic.schraudolph.org/bib2html/b2hd-Schraudolph98.html Centering Neural Network Gradient Factors]''. Neural Networks: Tricks of the Trade, 2nd ed. 2012
==2000 ...==
* [[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''2001'''). ''[https://nic.schraudolph.org/bib2html/b2hd-SchDaySej01.html Learning to Evaluate Go Positions via Temporal Difference Methods]''. [http://jasss.soc.surrey.ac.uk/7/1/reviews/takama.html Computational Intelligence in Games, Studies in Fuzziness and Soft Computing]. [https://www.springer.com/economics?SGWID=0-165-6-73479-0 Physica-Verlag], revised version of [[#1993|1993 paper]]
* [https://dblp.uni-trier.de/pers/hd/k/Klapper=Rybicka:Magdalena Magdalena Klapper-Rybicka], [[Nicol N. Schraudolph]], [[Jürgen Schmidhuber]] ('''2001'''). ''[https://nic.schraudolph.org/bib2html/b2hd-KlaSchSch01.html Unsupervised Learning in LSTM Recurrent Neural Networks]''. [https://dblp.uni-trier.de/db/conf/icann/icann2001.html ICANN 2001]
* [https://dblp.uni-trier.de/pers/hd/c/Chik:Desmond Desmond Chik], [https://dblp.uni-trier.de/pers/hd/t/Trumpf:Jochen Jochen Trumpf], [[Nicol N. Schraudolph]] ('''2007'''). ''[https://nic.schraudolph.org/bib2html/b2hd-ChiTruSch07.html 3D Hand Tracking in a Stochastic Approximation Setting]''. [https://dblp.uni-trier.de/db/conf/humo/humo2007.html Workshop on Human Motion 2007]
* [https://scholar.google.com/citations?user=tqcSvFIAAAAJ&hl=en S.V.N. Vishwanathan], [[Mathematician#KBorgwardt|Karsten Borgwardt]], [https://dblp.uni-trier.de/pers/hd/k/Kondor:Risi Risi Kondor], [[Nicol N. Schraudolph]] ('''2008'''). ''Graph Kernels''. [https://arxiv.org/abs/0807.0093 arXiv:0807.0093] <ref>[https://en.wikipedia.org/wiki/Graph_kernel Graph kernel from Wikipedia]</ref>
* [[Nicol N. Schraudolph]], [https://scholar.google.com.au/citations?user=8sq16RkAAAAJ&hl=en Dmitry Kamenetsky] ('''2008'''). ''Efficient Exact Inference in Planar Ising Models''. [https://arxiv.org/abs/0810.4401 arXiv:0810.4401]
==2010 ...==
* [https://scholar.google.com/citations?user=tqcSvFIAAAAJ&hl=en S.V.N. Vishwanathan], [[Nicol N. Schraudolph]], [https://dblp.uni-trier.de/pers/hd/k/Kondor:Risi Risi Kondor], [[Mathematician#KBorgwardt|Karsten Borgwardt]] ('''2010'''). ''[http://jmlr.csail.mit.edu/papers/v11/vishwanathan10a.html Graph Kernels]''. [https://de.wikipedia.org/wiki/Journal_of_Machine_Learning_Research Journal of Machine Learning Research], Vol. 11
* [[Nicol N. Schraudolph]] ('''2010'''). ''Polynomial-Time Exact Inference in NP-HardBinary MRFs via Reweighted Perfect Matching''. [https://dblp.uni-trier.de/db/journals/jmlr/jmlrp9.html AISTATS 2010], [http://proceedings.mlr.press/v9/schraudolph10a/schraudolph10a.pdf pdf]
* [[Nicol N. Schraudolph]] ('''2012'''). ''[https://link.springer.com/chapter/10.1007/978-3-642-35289-8_14 Centering Neural Network Gradient Factors]''. [https://link.springer.com/book/10.1007%2F978-3-642-35289-8 Neural Networks: Tricks of the Trade], 2nd edition
* [[Nicol N. Schraudolph]] ('''201?'''). ''Rapid Stochastic Gradient Descentfor Atomic Learning''. [https://en.wikipedia.org/wiki/NICTA NICTA], [https://www.yumpu.com/en/document/view/10166827/slides-machine-learning-theory slides] [http://hunch.net/~jl/conferences/atomic_learning/Nic.pdf as pdf], [http://canberra06.mlss.cc/slides/Nic-Schraudolph.pdf pdf]
=External Links=
* [https://nic.schraudolph.org/ Nic Schraudolph]
* [https://nic.schraudolph.org/teach/NNcourse/ Introduction to Neural Networks] by [[Nicol N. Schraudolph]] and [https://scholar.google.com/citations?user=E-vg2zQAAAAJ&hl=en Fred Cummins]
* [https://nic.schraudolph.org/teach/opengo.html Going for Go]
=References=
<references />
'''[[People|Up one level]]'''
[[Category:Researcher|Schraudolph]]
