Amos Storkey Explained

Amos James Storkey
Birth Date:	14 February 1971
Parents:	Alan Storkey, Elaine Storkey
Nationality:	British
Field:	Machine learning, artificial intelligence, computer science
Work Institution:	University of Edinburgh
Alma Mater:	Trinity College, Cambridge
Known For:	Storkey Learning Rule First Convolutional Network for Learning Go

Amos James Storkey (born 1971) is Professor of Machine Learning and Artificial Intelligence at the School of Informatics, University of Edinburgh.

Storkey studied mathematics at Trinity College, Cambridge and obtained his doctorate from Imperial College, London. In 1997 during his PhD, he worked on the Hopfield Network a form of recurrent artificial neural network popularized by John Hopfield in 1982. Hopfield nets serve as content-addressable ("associative") memory systems with binary threshold nodes and Storkey developed what became known as the "Storkey Learning Rule".^{[1] [2] [3] [4]}

Subsequently, he has worked on approximate Bayesian methods, machine learning in astronomy,^[5] graphical models, inference and sampling, and neural networks. Storkey joined the School of Informatics at the University of Edinburgh in 1999, was Microsoft Research Fellow from 2003 to 2004, appointed as reader in 2012, and to a personal chair in 2018. He is currently a Member of Institute for Adaptive and Neural Computation, Director of CDT in Data Science [2014-22] leading the Bayesian and Neural Systems Group.^[6] In December 2014, Clark and Storkey together published an innovative paper "Teaching Deep Convolutional Neural Networks to Play Go". Convolutional neural network (CNN, or ConvNet) is a class of deep neural networks, most commonly applied to analyzing visual imagery. Their paper showed that a Convolutional Neural Network trained by supervised learning from a database of human professional games could outperform GNU Go and win some games against Monte Carlo tree search Fuego 1.1 in a fraction of the time it took Fuego to play.^{[7] [8] [9] [10]}

Most cited work

• Antoniou A, Storkey A, Edwards H. Data augmentation generative adversarial networks. arXiv preprint arXiv:1711.04340. 2017 Nov 12.https://arxiv.org/pdf/1711.04340 According to Google Scholar, it has been cited 490 times.^[11]
• Burda Y, Edwards H, Storkey A, Klimov O. Exploration by random network distillation. arXiv preprint arXiv:1810.12894. 2018 Oct 30. https://arxiv.org/pdf/1810.12894.pdf%20http://arxiv.org/abs/1810.12894 According to Google Scholar, this paper has been cited 368 times
• Burda Y, Edwards H, Pathak D, Storkey A, Darrell T, Efros AA. Large-scale study of curiosity-driven learning. arXiv preprint arXiv:1808.04355. 2018 Aug 13. https://arxiv.org/pdf/1808.04355 According to Google Scholar, this paper has been cited 313 times
• Everingham M, Zisserman A, Williams CK, Van Gool L, Allan M, Bishop CM, Chapelle O, Dalal N, Deselaers T, Dorkó G, Duffner S. The 2005 pascal visual object classes challenge. InMachine Learning Challenges Workshop 2005 Apr 11 (pp. 117–176).https://hal.inria.fr/inria-00548597/file/EZKVAMCDDDDEDFGGJKKL.pdf Springer, Berlin, Heidelberg. According to Google Scholar, this paper has been cited 306 times
• Toussaint M, Storkey A. Probabilistic inference for solving discrete and continuous state Markov Decision Processes. InProceedings of the 23rd international conference on Machine learning 2006 Jun 25 (pp. 945–952).http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.60.9444&rep=rep1&type=pdf According to Google Scholar, this paper has been cited 217 times

Notes and References

1. Aggarwal, Charu C. "Neural Networks and Deep Learning" p240
2. https://saiconference.com/Downloads/FTC2017/Proceedings/62_Paper_426-Leveraging_Different_Learning_Rules_in_Hopfield.pdf Leveraging Different Learning Rules in Hopfield Nets for Multiclass Classification
3. Storkey, Amos. "Increasing the capacity of a Hopfield network without sacrificing functionality." Artificial Neural Networks – ICANN'97 (1997): 451-456.
4. Storkey, Amos. "Efficient Covariance Matrix Methods for Bayesian Gaussian Processes and Hopfield Neural Networks". PhD Thesis. University of London. (1999)
5. News: One giant scrapheap for mankind. BBC News. 15 April 2004.
6. Web site: Home . bayeswatch.com.
7. Web site: Why Neural Networks Look Set to Thrash the Best Human Go Players for the First Time. Emerging Technology from the. arXiv. MIT Technology Review.
8. Chris J Maddison, 'Move Evaluation in Go' Madhttp://www0.cs.ucl.ac.uk/staff/d.silver/web/Applications_files/deepgo.pdf
9. 1412.3409. Clark. Christopher. Teaching Deep Convolutional Neural Networks to Play Go. Storkey. Amos. cs.AI. 2014.
10. [Convolutional neural network]
11. https://scholar.google.com/scholar?hl=en&as_sdt=0%2C33&q=Amos+storkey&btnG= Google Scholar Author page, Accessed June 14, 2021