An Efficient EM-based Training Algorithm for Feedforward Neural Networks.

Farmer, James; Ji, Chuanyi; Ma, Sheng · Neural Netw · 1997

basic_science · Level V

Where this comes from

Abstract

A fast training algorithm is developed for two-layer feedforward neural networks based on a probabilistic model for hidden representations and the EM algorithm. The algorithm decomposes training the original two-layer networks into training a set of single neurons. The individual neurons are then trained via a linear weighted regression algorithm. Significant improvement on training speed has been made using this algorithm for several bench-mark problems. Copyright 1997 Elsevier Science Ltd. All Rights Reserved.