A neural network with localized receptive fields for visual pattern classification

Citation data:

Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005., Vol: 1, Page: 94-97

Publication Year:
2005
Usage 307
Downloads 300
Abstract Views 7
Citations 1
Citation Indexes 1
Repository URL:
http://ro.uow.edu.au/infopapers/2840
DOI:
10.1109/isspa.2005.1580204
Author(s):
Phung, Son Lam; Bouzerdoum, Abdesselam
Publisher(s):
Institute of Electrical and Electronics Engineers (IEEE)
Tags:
Engineering; Physical Sciences and Mathematics
conference paper description
We introduce a new neural network for 2D pattern classification. The new neural network, termed as localized receptive field neural network (RFNet), consists of a receptive field layer for 2D feature extraction, followed by one or more ID feedforward layers for feature classification. All synaptic weights and biases in the network are automatically determined through supervised training. In this paper, we derive five different training methods for the RFNet, namely gradient descent, gradient descent with momentum, resilient backpropagation, Polak-Ribiere conjugate gradient, and Levenberg-Marquadrt algorithm. We apply the RFNet to classify face and nonface patterns, and study the performances of the training algorithms and the RFNet classifier in this context. © 2005 IEEE.