Fuzzy associative memory network based on parameterized gathering operator

The neural network model Max-T FAM with the maximum operation and a t-norm T is an important generalized form of the classical fuzzy associative memory(FAM) network proposed by B.Kosko. This model has several disadvantages in its properties. Using a parameterized aggregating operator Vλ, we present a new generalized fuzzy associative memory(GFAM) network which is simple in computation and easy in implementation by hardware. All conjunctive operators of the interconnections of GFAM are chosen from a cluster {Vλ|λ ∈[0,1]}. The strict theoretical study reveals that the GFAM is uniformly continuous and has much higher mapping ability and stronger storage capability than all Max-T FAMs. From the theory of fuzzy relational equations, we derive and analyze a so-called Max-Min-λ learning algorithm for GFAM. Experimental comparisons of the storage capability have been made between GFAM and all Max-T FAMs. An application of GFAM to associative images is illustrated.