A connectionist method for pattern classification with diverse features

A novel connectionist method is proposed to simultaneously use diverse features in an optimal way for pattern classification. Unlike methods of combining multiple classifiers, a modular neural network architecture is proposed through use of soft competition among diverse features. Parameter estimation in the proposed architecture is treated as a maximum likelihood problem, and an Expectation-Maximization (EM) learning algorithm is developed for adjusting the parameters of the architecture. Comparative simulation results are presented for the real world problem of speaker identification. © 1998 Elsevier Science B.V. All rights reserved.