Premium
A novel logical neuron model
Author(s) -
Wang G. Y.,
Fisher P. S.
Publication year - 1999
Publication title -
international journal of intelligent systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.291
H-Index - 87
eISSN - 1098-111X
pISSN - 0884-8173
DOI - 10.1002/(sici)1098-111x(199912)14:12<1199::aid-int2>3.0.co;2-m
Subject(s) - artificial neural network , computer science , logical conjunction , biological neuron model , artificial intelligence , logical consequence , inference , programming language
The problem of representing and processing logical knowledge using a neural network is discussed. A novel neuron model, a triple‐valued logical neuron (TLN) is presented. There are two kinds of TLNs, triple‐valued “logical and” neuron (TLN‐AND) and triple‐valued “logical or” neuron (TLN‐OR). A multiple‐layer neural network (TLNN) made up of TLNs can implement a triple‐valued logical inference system. TLNN can thus form a base for representing logical knowledge using neural networks. ©1999 John Wiley & Sons, Inc.