Supervised Adaptive Hamming Net for Classification of Multiple-Valued Patterns

Abstract

A Supervised A daptive Hamming Net (SAHN) is introduced for incremental learning of recognition categories in response to arbitrary sequences of multiple-valued or binary-valued input patterns. The binary-valued SAHN derived from the Adaptive Hamming Net (AHN) is functionally equivalent t o a simplied ARTMAP, which is specically designed to establish many-to-one mappings. The generalization to learning multiple-valued input patterns is achieved by incorporating multiple-valued logic into the AHN. In this paper, we examine some useful properties of learning in a P-valued SAHN. In particular, an upper bound is derived on the number of epochs required by the P-valued SAHN to learn a list of input-output pairs that is repeatedly presented to the architecture. Furthermore, we connect the P-valued SAHN with the binary-valued SAHN via the thermometer code. Fast learning: When the Jth node in MAXNET is chosen, the template W J is updated according to the equation W new J = W old J u X :The adaptive w eight w J is updated according to the equationŵ new J