An EM-based algorithm for recurrent neural networks

A stochastic model is established for fully-connected recurrent neural networks with sigmoid units based on Gibbs distributions. The EM (expectation-maximization) algorithm with a mean field approximation is then applied to train recurrent networks through hidden state estimation. The resulting EM-b...

Full description

Saved in:
Bibliographic Details
Published inProceedings 1995 IEEE International Symposium on Information Theory p. 175
Main Authors Ma, S., Ji, C.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1995
Subjects
Computer networks
Convergence
Information theory
Jacobian matrices
Neural networks
Neurons
Recurrent neural networks
Testing
Online AccessGet full text
ISBN0780324536
9780780324534
DOI10.1109/ISIT.1995.531524

Cover

More Information
Summary:A stochastic model is established for fully-connected recurrent neural networks with sigmoid units based on Gibbs distributions. The EM (expectation-maximization) algorithm with a mean field approximation is then applied to train recurrent networks through hidden state estimation. The resulting EM-based algorithm, which reduces training the original recurrent network to training a set of individual feedforward neurons, simplifies the original training process and reduces the training time.
ISBN:0780324536
9780780324534
DOI:10.1109/ISIT.1995.531524