+612 9045 4394
 
CHECKOUT
Graphical Models : Foundations of Neural Computation - Michael I. Jordan

Graphical Models

Foundations of Neural Computation

By: Michael I. Jordan (Editor), Terrence J. Sejnowski (Editor)

Paperback Published: 3rd December 2001
ISBN: 9780262600422
Number Of Pages: 434
For Ages: 18+ years old

Share This Book:

Paperback

RRP $99.99
$78.40
22%
OFF
Ships in 15 business days

This book exemplifies the interplay between the general formal framework of graphical models and the exploration of new algorithm and architectures. The selections range from foundational papers of historical importance to results at the cutting edge of research.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.ContributorsH. 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. Rodriguez, L. K. Saul, Terrence J. Sejnowski, P. Smyth, M. E. Tipping, V. Tresp, Y. Weiss

Series Forewordp. vii
Sourcesp. ix
Introductionp. xi
Probabilistic Independence Networks for Hidden Markov Probability Modelsp. 1
Learning and Relearning in Boltzmann Machinesp. 45
Learning in Boltzmann Treesp. 77
Deterministic Boltzmann Learning Performs Steepest Descent in Weight-Spacep. 89
Attractor Dynamics in Feedforward Neural Networksp. 97
Efficient Learning in Boltzmann Machines Using Linear Response Theoryp. 121
Asymmetric Parallel Boltzmann Machines Are Belief Networksp. 141
Variational Learning in Nonlinear Gaussian Belief Networksp. 145
Mixtures of Probabilistic Principal Component Analyzersp. 167
Independent Factor Analysisp. 207
Hierarchical Mixtures of Experts and the EM Algorithmp. 257
Hidden Neural Networksp. 291
Variational Learning for Switching State-Space Modelsp. 315
Nonlinear Time-Series Prediction with Missing and Noisy Datap. 349
Correctness of Local Probability Propagation in Graphical Models with Loopsp. 367
Indexp. 409
Table of Contents provided by Syndetics. All Rights Reserved.

ISBN: 9780262600422
ISBN-10: 0262600420
Series: Graphical Models
Audience: Professional
For Ages: 18+ years old
Format: Paperback
Language: English
Number Of Pages: 434
Published: 3rd December 2001
Publisher: MIT Press Ltd
Country of Publication: US
Dimensions (cm): 22.9 x 15.2  x 2.5
Weight (kg): 0.6