Supervised adaptive Hamming net for classification of multiple-valued patterns.

C. A. Hung*, Sheng-Fuu Lin

*Corresponding author for this work

Research output: Contribution to journalArticle

1 Scopus citations

Abstract

A Supervised Adaptive 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 to a simplified ARTMAP, which is specifically 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.

Original languageEnglish
Pages (from-to)181-200
Number of pages20
JournalInternational journal of neural systems
Volume8
Issue number2
DOIs
StatePublished - 1 Jan 1997

Fingerprint Dive into the research topics of 'Supervised adaptive Hamming net for classification of multiple-valued patterns.'. Together they form a unique fingerprint.

  • Cite this