25,161
edits
Changes
Created page with "'''Home * People * Amos Storkey''' FILE:AmosStorkey.jpg|border|right|thumb|link=http://homepages.inf.ed.ac.uk/amos/introduction.html| Amos Storkey <ref>[h..."
'''[[Main Page|Home]] * [[People]] * Amos Storkey'''
[[FILE:AmosStorkey.jpg|border|right|thumb|link=http://homepages.inf.ed.ac.uk/amos/introduction.html| Amos Storkey <ref>[http://homepages.inf.ed.ac.uk/amos/introduction.html Amos Storkey - Introduction]</ref> ]]
'''Amos James Storkey''',<br/>
a British computer scientist and [https://en.wikipedia.org/wiki/Reader_%28academic_rank%29 reader] (associate professor) at Institute for Adaptive and Neural Computation, School of Informatics, [[University of Edinburgh]].
He holds a Ph.D. in 1999 on [[Neural Networks|neural networks]] from the Neural Systems Group, Department of Electrical Engineering, [https://en.wikipedia.org/wiki/Imperial_College_London Imperial College London] under [[Mathematician#PDeWilde|Philippe De Wilde]] <ref>[http://homepages.inf.ed.ac.uk/amos/background.html Amos Storkey - Background]</ref>.
His research covers [[Learning|machine learning]] applied to [https://en.wikipedia.org/wiki/Prediction_market prediction market], [https://en.wikipedia.org/wiki/Astronomy astronomy] and changing [https://en.wikipedia.org/wiki/Environment_%28systems%29 environments], [https://en.wikipedia.org/wiki/Bayesian_statistics#Statistical_modeling bayesian modeling] in [https://en.wikipedia.org/wiki/Neuroimaging neuroimaging],
learning and [https://en.wikipedia.org/wiki/Inference inference], dynamical [https://en.wikipedia.org/wiki/Boltzmann_machine Boltzmann machine] models, and scalable [[Deep Learning|deep learning]] <ref>[http://homepages.inf.ed.ac.uk/amos/introduction.html Amos Storkey - Introduction]</ref>.
=DCNNs in Go=
As reported in their 2014 paper ''Teaching Deep Convolutional Neural Networks to Play Go'', Amos Storkey along with [[Christopher Clark]] trained an 8-layer [[Go#CNN|convolutional neural network]] <ref>[https://en.wikipedia.org/wiki/Convolutional_neural_network#Playing_Go Convolutional neural network - Playing Go - Wikipedia]</ref> by [[Supervised Learning|supervised learning]] from a database of human professional games to predict the moves made by expert [[Go]] players. They introduced a number of novel techniques, including a method of tying weights in the network to 'hard code' symmetries that are expect to exist in the target function, and demonstrated in an ablation study they considerably improve performance. Their final networks can consistently defeat [[Gnu Go]] , indicating it is state of the art among programs that do not use [[Monte-Carlo Tree Search]], and was also able to win some games against [[Fuego]] while using a fraction of the playing time
<ref>[[Christopher Clark]], [[Amos Storkey]] ('''2014'''). ''Teaching Deep Convolutional Neural Networks to Play Go''. [https://arxiv.org/abs/1412.3409 arXiv:1412.3409]</ref>
<ref>[http://computer-go.org/pipermail/computer-go/2014-December/007041.html Teaching Deep Convolutional Neural Networks to Play Go] by [[Hiroshi Yamashita]], [http://computer-go.org/pipermail/computer-go/ The Computer-go Archives], December 19, 2014</ref>
<ref>[http://computer-go.org/pipermail/computer-go/2014-December/007010.html Teaching Deep Convolutional Neural Networks to Play Go] by [[Hiroshi Yamashita]], [http://computer-go.org/pipermail/computer-go/ The Computer-go Archives], December 14, 2014</ref>
<ref>[http://www.technologyreview.com/view/533496/why-neural-networks-look-set-to-thrash-the-best-human-go-players-for-the-first-time/ Why Neural Networks Look Set to Thrash the Best Human Go Players for the First Time] | [https://en.wikipedia.org/wiki/MIT_Technology_Review MIT Technology Review], December 15, 2014</ref>
<ref>[http://www.talkchess.com/forum/viewtopic.php?t=54663 Teaching Deep Convolutional Neural Networks to Play Go] by [[Michel Van den Bergh]], [[CCC]], December 16, 2014</ref> .
=Selected Publications=
<ref>[https://dblp.uni-trier.de/pers/hd/s/Storkey:Amos_J= dblp: Amos J. Storkey]</ref>
==1997 ...==
* [[Amos Storkey]] ('''1997'''). ''[https://link.springer.com/chapter/10.1007/BFb0020196 Increasing the Capacity of a Hopfield Network without Sacrificing Functionality]''. [https://dblp.uni-trier.de/db/conf/icann/icann1997.html ICANN 1997], [https://homepages.inf.ed.ac.uk/amos/publications/Storkey1997IncreasingtheCapacityoftheHopfieldNetworkwithoutSacrificingFunctionality.pdf pdf] <ref>[https://en.wikipedia.org/wiki/Hopfield_network Hopfield network from Wikipedia]</ref>
* [[Amos Storkey]] ('''1999'''). ''Efficient Covariance Matrix Methods for Bayesian Gaussian Processes and Hopfield Neural Networks''. Ph.D. thesis, [https://en.wikipedia.org/wiki/Imperial_College_London Imperial College London], supervisor [[Mathematician#PDeWilde|Philippe De Wilde]], [http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.33.3383 CiteSeerX]
==2000 ...==
* [[Amos Storkey]] ('''2002'''). ''[https://papers.nips.cc/paper/2271-dynamic-structure-super-resolution Dynamic Structure Super-Resolution]''. [https://dblp.uni-trier.de/db/conf/nips/nips2002.html NIPS 2002]
* [[Amos Storkey]] ('''2003'''). ''[https://papers.nips.cc/paper/2505-generalised-propagation-for-fast-fourier-transforms-with-partial-or-missing-data Generalised Propagation for Fast Fourier Transforms with Partial or Missing Data]''. [https://dblp.uni-trier.de/db/conf/nips/nips2003.html NIPS 2003]
* [https://www.leeds.ac.uk/secretariat/obituaries/2012/everingham_mark.html Mark Everingham], [[Mathematician#AZisserman|Andrew Zisserman]], [https://homepages.inf.ed.ac.uk/ckiw/ Chris Williams], [https://scholar.google.com/citations?user=TwMib_QAAAAJ&hl=en Luc van Gool], [http://www.morayallan.com/ Moray Allan], [[Amos Storkey]], et al. ('''2005'''). ''The 2005 PASCAL Visual Object Classes Challenge''. [https://dblp.uni-trier.de/db/conf/mlcw/mlcw2005.html MLCW 2005], [https://hal.inria.fr/inria-00548597/document pdf] <ref>[http://host.robots.ox.ac.uk/pascal/VOC/ The PASCAL Visual Object Classes Homepage]</ref> <ref>[[Mathematician#AZisserman|Andrew Zisserman]], [https://scholar.google.com/citations?user=GYksTEEAAAAJ&hl=en John Winn], [https://en.wikipedia.org/wiki/Andrew_Fitzgibbon_(engineer) Andrew Fitzgibbon], [https://scholar.google.com/citations?user=TwMib_QAAAAJ&hl=en Luc van Gool], [https://scholar.google.com/citations?user=NCtKHnQAAAAJ&hl=en Josef Sivic], [https://homepages.inf.ed.ac.uk/ckiw/ Chris Williams], [https://scholar.google.com/citations?user=5VJ4YPQAAAAJ&hl=en David Hogg] ('''2012'''). ''[https://www.computer.org/csdl/journal/tp/2012/11/ttp2012112081/13rRUxNW1UY In Memoriam: Mark Everingham]''. [[IEEE#TPAMI|IEEE Transactions on Pattern Analysis and Machine Intelligence]], Vol. 34, No. 11</ref>
* [[Amos Storkey]], [https://www.k.u-tokyo.ac.jp/pros-e/person/masashi_sugiyama/masashi_sugiyama.htm Masashi Sugiyama] ('''2006'''). ''[http://papers.neurips.cc/paper/3019-mixture-regression-for-covariate-shift Mixture Regression for Covariate Shift]''. [https://dblp.uni-trier.de/db/conf/nips/nips2006.html NIPS 2006]
* [https://www.indii.org/research/ Lawrence Murray], [[Amos Storkey]] ('''2007'''). ''Continuous Time Particle Filtering for fMRI''. [https://dblp.uni-trier.de/db/conf/nips/nips2007.html NIPS 2007], [https://homepages.inf.ed.ac.uk/amos/publications/MurrayStorkey2008ContinuousTimeParticleFilterFmri.pdf pdf] <ref>[https://en.wikipedia.org/wiki/Functional_magnetic_resonance_imaging Functional magnetic resonance imaging - Wikipedia]</ref>
==2010 ...==
* [[Amos Storkey]] ('''2011'''). ''Machine Learning Markets''. [http://arxiv.org/abs/1106.4509 arXiv:1106.4509]
* [[Amos Storkey]] ('''2013'''). ''Dynamic Trees: A Structured Variational Method Giving Efficient Propagation Rules''. [https://arxiv.org/abs/1301.3895 arXiv:1301.3895]
* [[Christopher Clark]], [[Amos Storkey]] ('''2014'''). ''Teaching Deep Convolutional Neural Networks to Play Go''. [https://arxiv.org/abs/1412.3409 arXiv:1412.3409]
* [[Christopher Clark]], [[Amos Storkey]] ('''2015'''). ''Training Deep Convolutional Neural Networks to Play Go''. [https://dblp.uni-trier.de/db/conf/icml/icml2015.html ICML 2015], [http://proceedings.mlr.press/v37/clark15.pdf pdf]
* [https://scholar.google.co.uk/citations?user=0o470HsAAAAJ&hl=en Harrison Edwards], [[Amos Storkey]] ('''2016'''). ''Towards a Neural Statistician''. [https://arxiv.org/abs/1606.02185 arXiv:1606.02185]
* [https://sites.google.com/site/yburda/ Yuri Burda], [https://scholar.google.co.uk/citations?user=0o470HsAAAAJ&hl=en Harrison Edwards], [[Amos Storkey]], [https://scholar.google.com/citations?user=tsFD4tUAAAAJ&hl=en Oleg Klimov] ('''2018'''). ''Exploration by Random Network Distillation''. [https://arxiv.org/abs/1810.12894 arXiv:1810.12894]
=External Links=
* [http://homepages.inf.ed.ac.uk/amos/introduction.html Amos Storkey]
* [https://scholar.google.com/citations?user=3Rlc8EAAAAAJ Amos Storkey - Google Scholar Citations]
* [https://genealogy.math.ndsu.nodak.edu/id.php?id=209172 Amos Storkey - The Mathematics Genealogy Project]
* [https://www.research.ed.ac.uk/portal/en/clippings/christopher-clark-and-amos-storkey-apply-new-algorithms-to-ancient-chinese-game-go(75c8bf11-aab5-467a-8c73-a1f04022bdab).html Christopher Clark and Amos Storkey apply new algorithms to ancient Chinese game 'Go' - Edinburgh Research Explorer]
=References=
<references />
'''[[People|Up one level]]'''
[[Category:Mathematician|Storkey]]
[[Category:Researcher|Storkey]]
[[FILE:AmosStorkey.jpg|border|right|thumb|link=http://homepages.inf.ed.ac.uk/amos/introduction.html| Amos Storkey <ref>[http://homepages.inf.ed.ac.uk/amos/introduction.html Amos Storkey - Introduction]</ref> ]]
'''Amos James Storkey''',<br/>
a British computer scientist and [https://en.wikipedia.org/wiki/Reader_%28academic_rank%29 reader] (associate professor) at Institute for Adaptive and Neural Computation, School of Informatics, [[University of Edinburgh]].
He holds a Ph.D. in 1999 on [[Neural Networks|neural networks]] from the Neural Systems Group, Department of Electrical Engineering, [https://en.wikipedia.org/wiki/Imperial_College_London Imperial College London] under [[Mathematician#PDeWilde|Philippe De Wilde]] <ref>[http://homepages.inf.ed.ac.uk/amos/background.html Amos Storkey - Background]</ref>.
His research covers [[Learning|machine learning]] applied to [https://en.wikipedia.org/wiki/Prediction_market prediction market], [https://en.wikipedia.org/wiki/Astronomy astronomy] and changing [https://en.wikipedia.org/wiki/Environment_%28systems%29 environments], [https://en.wikipedia.org/wiki/Bayesian_statistics#Statistical_modeling bayesian modeling] in [https://en.wikipedia.org/wiki/Neuroimaging neuroimaging],
learning and [https://en.wikipedia.org/wiki/Inference inference], dynamical [https://en.wikipedia.org/wiki/Boltzmann_machine Boltzmann machine] models, and scalable [[Deep Learning|deep learning]] <ref>[http://homepages.inf.ed.ac.uk/amos/introduction.html Amos Storkey - Introduction]</ref>.
=DCNNs in Go=
As reported in their 2014 paper ''Teaching Deep Convolutional Neural Networks to Play Go'', Amos Storkey along with [[Christopher Clark]] trained an 8-layer [[Go#CNN|convolutional neural network]] <ref>[https://en.wikipedia.org/wiki/Convolutional_neural_network#Playing_Go Convolutional neural network - Playing Go - Wikipedia]</ref> by [[Supervised Learning|supervised learning]] from a database of human professional games to predict the moves made by expert [[Go]] players. They introduced a number of novel techniques, including a method of tying weights in the network to 'hard code' symmetries that are expect to exist in the target function, and demonstrated in an ablation study they considerably improve performance. Their final networks can consistently defeat [[Gnu Go]] , indicating it is state of the art among programs that do not use [[Monte-Carlo Tree Search]], and was also able to win some games against [[Fuego]] while using a fraction of the playing time
<ref>[[Christopher Clark]], [[Amos Storkey]] ('''2014'''). ''Teaching Deep Convolutional Neural Networks to Play Go''. [https://arxiv.org/abs/1412.3409 arXiv:1412.3409]</ref>
<ref>[http://computer-go.org/pipermail/computer-go/2014-December/007041.html Teaching Deep Convolutional Neural Networks to Play Go] by [[Hiroshi Yamashita]], [http://computer-go.org/pipermail/computer-go/ The Computer-go Archives], December 19, 2014</ref>
<ref>[http://computer-go.org/pipermail/computer-go/2014-December/007010.html Teaching Deep Convolutional Neural Networks to Play Go] by [[Hiroshi Yamashita]], [http://computer-go.org/pipermail/computer-go/ The Computer-go Archives], December 14, 2014</ref>
<ref>[http://www.technologyreview.com/view/533496/why-neural-networks-look-set-to-thrash-the-best-human-go-players-for-the-first-time/ Why Neural Networks Look Set to Thrash the Best Human Go Players for the First Time] | [https://en.wikipedia.org/wiki/MIT_Technology_Review MIT Technology Review], December 15, 2014</ref>
<ref>[http://www.talkchess.com/forum/viewtopic.php?t=54663 Teaching Deep Convolutional Neural Networks to Play Go] by [[Michel Van den Bergh]], [[CCC]], December 16, 2014</ref> .
=Selected Publications=
<ref>[https://dblp.uni-trier.de/pers/hd/s/Storkey:Amos_J= dblp: Amos J. Storkey]</ref>
==1997 ...==
* [[Amos Storkey]] ('''1997'''). ''[https://link.springer.com/chapter/10.1007/BFb0020196 Increasing the Capacity of a Hopfield Network without Sacrificing Functionality]''. [https://dblp.uni-trier.de/db/conf/icann/icann1997.html ICANN 1997], [https://homepages.inf.ed.ac.uk/amos/publications/Storkey1997IncreasingtheCapacityoftheHopfieldNetworkwithoutSacrificingFunctionality.pdf pdf] <ref>[https://en.wikipedia.org/wiki/Hopfield_network Hopfield network from Wikipedia]</ref>
* [[Amos Storkey]] ('''1999'''). ''Efficient Covariance Matrix Methods for Bayesian Gaussian Processes and Hopfield Neural Networks''. Ph.D. thesis, [https://en.wikipedia.org/wiki/Imperial_College_London Imperial College London], supervisor [[Mathematician#PDeWilde|Philippe De Wilde]], [http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.33.3383 CiteSeerX]
==2000 ...==
* [[Amos Storkey]] ('''2002'''). ''[https://papers.nips.cc/paper/2271-dynamic-structure-super-resolution Dynamic Structure Super-Resolution]''. [https://dblp.uni-trier.de/db/conf/nips/nips2002.html NIPS 2002]
* [[Amos Storkey]] ('''2003'''). ''[https://papers.nips.cc/paper/2505-generalised-propagation-for-fast-fourier-transforms-with-partial-or-missing-data Generalised Propagation for Fast Fourier Transforms with Partial or Missing Data]''. [https://dblp.uni-trier.de/db/conf/nips/nips2003.html NIPS 2003]
* [https://www.leeds.ac.uk/secretariat/obituaries/2012/everingham_mark.html Mark Everingham], [[Mathematician#AZisserman|Andrew Zisserman]], [https://homepages.inf.ed.ac.uk/ckiw/ Chris Williams], [https://scholar.google.com/citations?user=TwMib_QAAAAJ&hl=en Luc van Gool], [http://www.morayallan.com/ Moray Allan], [[Amos Storkey]], et al. ('''2005'''). ''The 2005 PASCAL Visual Object Classes Challenge''. [https://dblp.uni-trier.de/db/conf/mlcw/mlcw2005.html MLCW 2005], [https://hal.inria.fr/inria-00548597/document pdf] <ref>[http://host.robots.ox.ac.uk/pascal/VOC/ The PASCAL Visual Object Classes Homepage]</ref> <ref>[[Mathematician#AZisserman|Andrew Zisserman]], [https://scholar.google.com/citations?user=GYksTEEAAAAJ&hl=en John Winn], [https://en.wikipedia.org/wiki/Andrew_Fitzgibbon_(engineer) Andrew Fitzgibbon], [https://scholar.google.com/citations?user=TwMib_QAAAAJ&hl=en Luc van Gool], [https://scholar.google.com/citations?user=NCtKHnQAAAAJ&hl=en Josef Sivic], [https://homepages.inf.ed.ac.uk/ckiw/ Chris Williams], [https://scholar.google.com/citations?user=5VJ4YPQAAAAJ&hl=en David Hogg] ('''2012'''). ''[https://www.computer.org/csdl/journal/tp/2012/11/ttp2012112081/13rRUxNW1UY In Memoriam: Mark Everingham]''. [[IEEE#TPAMI|IEEE Transactions on Pattern Analysis and Machine Intelligence]], Vol. 34, No. 11</ref>
* [[Amos Storkey]], [https://www.k.u-tokyo.ac.jp/pros-e/person/masashi_sugiyama/masashi_sugiyama.htm Masashi Sugiyama] ('''2006'''). ''[http://papers.neurips.cc/paper/3019-mixture-regression-for-covariate-shift Mixture Regression for Covariate Shift]''. [https://dblp.uni-trier.de/db/conf/nips/nips2006.html NIPS 2006]
* [https://www.indii.org/research/ Lawrence Murray], [[Amos Storkey]] ('''2007'''). ''Continuous Time Particle Filtering for fMRI''. [https://dblp.uni-trier.de/db/conf/nips/nips2007.html NIPS 2007], [https://homepages.inf.ed.ac.uk/amos/publications/MurrayStorkey2008ContinuousTimeParticleFilterFmri.pdf pdf] <ref>[https://en.wikipedia.org/wiki/Functional_magnetic_resonance_imaging Functional magnetic resonance imaging - Wikipedia]</ref>
==2010 ...==
* [[Amos Storkey]] ('''2011'''). ''Machine Learning Markets''. [http://arxiv.org/abs/1106.4509 arXiv:1106.4509]
* [[Amos Storkey]] ('''2013'''). ''Dynamic Trees: A Structured Variational Method Giving Efficient Propagation Rules''. [https://arxiv.org/abs/1301.3895 arXiv:1301.3895]
* [[Christopher Clark]], [[Amos Storkey]] ('''2014'''). ''Teaching Deep Convolutional Neural Networks to Play Go''. [https://arxiv.org/abs/1412.3409 arXiv:1412.3409]
* [[Christopher Clark]], [[Amos Storkey]] ('''2015'''). ''Training Deep Convolutional Neural Networks to Play Go''. [https://dblp.uni-trier.de/db/conf/icml/icml2015.html ICML 2015], [http://proceedings.mlr.press/v37/clark15.pdf pdf]
* [https://scholar.google.co.uk/citations?user=0o470HsAAAAJ&hl=en Harrison Edwards], [[Amos Storkey]] ('''2016'''). ''Towards a Neural Statistician''. [https://arxiv.org/abs/1606.02185 arXiv:1606.02185]
* [https://sites.google.com/site/yburda/ Yuri Burda], [https://scholar.google.co.uk/citations?user=0o470HsAAAAJ&hl=en Harrison Edwards], [[Amos Storkey]], [https://scholar.google.com/citations?user=tsFD4tUAAAAJ&hl=en Oleg Klimov] ('''2018'''). ''Exploration by Random Network Distillation''. [https://arxiv.org/abs/1810.12894 arXiv:1810.12894]
=External Links=
* [http://homepages.inf.ed.ac.uk/amos/introduction.html Amos Storkey]
* [https://scholar.google.com/citations?user=3Rlc8EAAAAAJ Amos Storkey - Google Scholar Citations]
* [https://genealogy.math.ndsu.nodak.edu/id.php?id=209172 Amos Storkey - The Mathematics Genealogy Project]
* [https://www.research.ed.ac.uk/portal/en/clippings/christopher-clark-and-amos-storkey-apply-new-algorithms-to-ancient-chinese-game-go(75c8bf11-aab5-467a-8c73-a1f04022bdab).html Christopher Clark and Amos Storkey apply new algorithms to ancient Chinese game 'Go' - Edinburgh Research Explorer]
=References=
<references />
'''[[People|Up one level]]'''
[[Category:Mathematician|Storkey]]
[[Category:Researcher|Storkey]]
