Accession Number : ADP007152

Title :   Classification by EM-Trained Dynamic Artificial Neural Nets Based on Hidden Perceptrons,

Corporate Author : IBM THOMAS J WATSON RESEARCH CENTER YORKTOWN HEIGHTS NY

Personal Author(s) : Nadas, Arthur

Report Date : 1992

Pagination or Media Count : 4

Abstract : We propose to classify points in R d by functions related to two-layer (a single hidden layer) feedforward artificial neural nets (ANNs). These functions, dubbed dynamic ANNs (DANNs), arise in a rather natural way from probabilistic and also statistical considerations. We treat the binary classification problem and outline an approach to the n-ary classification problem. There are two key ideas. The probabilistic idea is that DANNs are conditional probabilities certain mixture models. The statistical idea is that these models, and hence the DANNs defined by them, are conveniently trainable by an expectation - maximization (EM) algorithm.

Descriptors :   *NEURAL NETS, APPROACH, CLASSIFICATION, DYNAMICS, FUNCTIONS, MIXTURES, MODELS.

Subject Categories : Biology

Distribution Statement : APPROVED FOR PUBLIC RELEASE