Nicol N. Schraudolph

From Chessprogramming wiki
Jump to: navigation, search

Home * People * Nicol N. Schraudolph

Nic Schraudolph [1]

Nicol N. (Nic) Schraudolph,
a German computer scientist, independent researcher and consultant in machine learning and optimization, in particular stochastic gradient descent. He received a B.Sc. degree in computer science from the University of Essex in 1988, and M.Sc. and Ph.D. degrees in computer science and cognitive science from University of California, San Diego, the Ph.D. in 1995 on optimization of entropy with neural networks under Terrence J. Sejnowski [2]. His previous research affiliations include NICTA Canberra, ETH Zurich and Dalle Molle Institute for Artificial Intelligence Research, Lugano.

Learning Go

Along with Peter Dayan and his advisor, Terrence J. Sejnowski, Nicol Schraudolph applied temporal difference learning to an evaluation function in the game of Go, as published in 1993 [3], and in 2001 [4].


A modular network architecture that takes advantage of board symmetries,
translation invariance and localized reinforcement to evaluate Go positions [5]

Selected Publications

[6] [7] [8]

1991 ...

2000 ...

2010 ...

External Links


Up one level