An intuitionistic fuzzy associative memory network and its learning rule

Abstract

Intuitionistic fuzzy set (IFS) is a generalization of fuzzy set by introducing an additional attribute parameter called non-membership degree. In this paper, an intuitionistic fuzzy associative memory (IFAM) network is proposed by combining IFS with associative memory network. Based on Godel fuzzy implication operator and its dual fuzzy co-implication operator, a learning rule for multiple intuitionistic fuzzy pattern pairs in IFAM is presented. The storage capacity of IFAM is also investigated. It is shown that under certain conditions, the proposed rule can efficiently encode multiple intuitionistic fuzzy pattern pairs into a single IFAM and achieve perfect association of these pairs.