Expanding the Structure Inhibitory Artificial Neural Network Classifiers

Authors

Ganesh Arulampalam, Edith Cowan University
Abdesselam Bouzerdoum, Edith Cowan University

Document Type

Conference Proceeding

Keywords

[RSTDPub], Artificial neural networks, Neurons, Image processing, Cellular neural networks, Differential equations, Multilayer perceptrons, Australia, Gain control, Programmable control, Adaptive control

Publisher

IEEE

Faculty

Faculty of Computing, Health and Science

School

School of Engineering and Mathematics

RAS ID

15

Comments

Arulampalam, G., & Bouzerdoum, A. (2002). Expanding the structure of shunting inhibitory artificial neural network classifiers. Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on, Honolulu, USA (pp. 2855-2860). Available here

Abstract

Shunting inhibitory artificial neural networks (SIANNs) are biologically inspired networks in which the neurons interact via a nonlinear mechanism called shunting inhibition. They are capable of producing complex, nonlinear decision boundaries. The structure and operation of feedforward SIANNs and some enhancements are presented. They are applied to several classification problems, and their performance is compared to that of the multilayer perceptron classifier.