Asymptotically Stable Multi-valued Many-to-many Associative Memory Neural Network and Its Application in Image Retrieval

As an important artificial neural network, associative memory model can be employed to mimic human thinking and machine intelligence. In this paper, first, a multi-valued many-to-many Gaussian associative memory model (MGAM) is proposed by introducing the Gaussian unidirectional associative memory model (GUAM) and Gaussian bidirectional associative memory model (GBAM) into Hattori et al’s multi-module associative memory model ((MMA)). Second, the MGAM’s asymptotical stability is proved theoretically in both synchronous and asynchronous update modes, which ensures that the stored patterns become the MGAM’s stable points. Third, by substituting the general similarity metric for the negative squared Euclidean distance in MGAM, the generalized multivalued many-to-many Gaussian associative memory model (GMGAM) is presented, which makes the MGAM become its special case. Finally, we investigate the MGAM’s application in association-based image retrieval, and the computer simulation results verify the MGAM’s robust performance.