Title :
Beyond the binary Boltzmann machine
Author :
Anderson, N.H. ; Titterington, D.M.
Author_Institution :
Dept. of Stat., Glasgow Univ., UK
fDate :
9/1/1995 12:00:00 AM
Abstract :
The definition of the usual Boltzmann machine is extended to allow for neurons with polytomous (multicategory) rather than simply binary responses. Updating rules are defined along with the associated stationary distributions, and an alternating minimization method is described for the purposes of training. Emphasis is placed on the relevance of statistical ideas, including polytomous logistic regression, the iterative proportional fitting procedure and the EM algorithm
Keywords :
Boltzmann machines; iterative methods; minimisation; recurrent neural nets; statistical analysis; EM algorithm; alternating minimization method; binary Boltzmann machine; iterative proportional fitting procedure; polytomous logistic regression; polytomous responses; Information geometry; Iterative algorithms; Logistics; Minimization methods; Neurons; Probability distribution; State-space methods; Statistics; Stochastic processes; Terminology;
Journal_Title :
Neural Networks, IEEE Transactions on
