A neural network which learns decision boundaries with nonlinear clustering
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Presents a novel neural network which works as a classifier. It uses Euclidean distance similarity measurement to form clusters which are represented by output units. Uniquely, output units in the proposed network have nonlinear hard-limiter activation functions. Through this nonlinear activation function, complex decision boundaries from input patterns can be approximated. Furthermore, it does not forget previously remembered training patterns as it remembers newly shown patterns. This is shown with illustrative proofs. Simulation results are presented and compared with those from the backpropagation neural network. They demonstrate that the network described, with its simple architecture and learning, it is able to capture continuous distributions of complex decision boundaries from discrete patterns Author(s) Chu, Y.C. Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Shatin, Hong Kong Klassen, M.Keywords
This publication has 3 references indexed in Scilit:
- A texture classifier based on neural network principlesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Pattern classification using self-organizing feature mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Enhancing supervised learning algorithms via self-organizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989