This paper proposes an associative memory model based on a coupled system\nof Gaussian maps. A one-dimensional Gaussian map describes a discrete-time\ndynamical system, and the coupled system of Gaussian maps can generate various\nphenomena including asymmetric fixed and periodic points. The Gaussian\nassociative memory can effectively recall one of the stored patterns, which were\ntriggered by an input pattern by associating the asymmetric two-periodic\npoints observed in the coupled system with the binary values of output patterns.\nTo investigate the Gaussian associative memory model, we formed its\nreduced model and analyzed the bifurcation structure. Pseudo-patterns were\nobserved for the proposed model along with other conventional associative\nmemory models, and the obtained patterns were related to the high-order or\nquasi-periodic points and the chaotic trajectories. In this paper, the structure\nof the Gaussian associative memory and its reduced models are introduced as\nwell as the results of the bifurcation analysis are presented. Furthermore, the\noutput sequences obtained from simulation of the recalling process are presented.\nWe discuss the mechanism and the characteristics of the Gaussian\nassociative memory based on the results of the analysis and the simulations\nconducted.
Loading....