Discriminative multi-layer feed-forward networks

Abstract

The authors propose a new family of multi-layer, feed-forward network (FFN) architectures. This framework allows examination of several feed-forward networks, including the well-known multi-layer perceptron (MLP) network, the likelihood network (LNET) and the distance network (DNET), in a unified manner. They then introduce a novel formulation which embeds network parameters into a functional form of the classifier design objective so that the network's parameters can be adjusted by gradient search algorithms, such as the generalized probabilistic descent (GPD) method. They evaluate several discriminative three-layer networks by performing a pattern classification task. They demonstrate that the performance of a network can be significantly improved when discriminative formulations are incorporated into the design of the pattern classification networks.<>