Study of a bionic pattern classifier based on olfactory neural system

Abstract

Simulating biological olfactory neural system, K III network, which is a high-dimensional chaotic neural network, is designed in this paper. Different from conventional artificial neural network, the K III network works in its chaotic trajectory. It can simulate not only the output EEG waveform observed in electrophysiological experiments, but also the biological intelligence for pattern classification. The simulation analysis and application to the recognition of handwriting numerals are presented here. The classification performance of the K III network at different noise levels was also investigated.