Graphical models : foundations of neural computation / edited by Michael I. Jordan and Terrence J. Sejnowski.

Graphical models : foundations of neural computation / edited by Michael I. Jordan and Terrence J. Sejnowski.

0262291207 (electronic bk.)
9780262291200 (electronic bk.)
0262600420
9780262600422

Cambridge, Mass. : MIT Press, ©2001.

English

1 online resource (xxiv, 421 pages) : illustrations.

QA76.87 .G72 2001eb

006.3/2

Graphical models use graphs to represent and manipulate joint probability distributions. They have their roots in artificial intelligence, statistics, and neural networks. The clean mathematical formalism of the graphical models framework makes it possible to understand a wide variety of network-based approaches to computation, and in particular to understand many neural network algorithms and architectures as instances of a broader probabilistic methodology. It also makes it possible to identify novel features of neural network algorithms and architectures and to extend them to more general graphical models.This book exemplifies the interplay between the general formal framework of graphical models and the exploration of new algorithms and architectures. The selections range from foundational papers of historical importance to results at the cutting edge of research.Contributors H. Attias, C. M. Bishop, B. J. Frey, Z. Ghahramani, D. Heckerman, G. E. Hinton, R. Hofmann, R. A. Jacobs, Michael I. Jordan, H. J. Kappen, A. Krogh, R. Neal, S. K. Riis, F. B. Rodr<u+0083>iguez, L. K. Saul, Terrence J. Sejnowski, P. Smyth, M. E. Tipping, V. Tresp, Y. Weiss.

"A Bradford book."

Access limited to authorized users.

OCLC-licensed vendor bibliographic record.

Online Access through The MIT Press Direct
OCLC metadata license agreement

Online Resources > Ebooks
All Resources