Memoirs of the Faculty of Engineering, Okayama University 27巻 2号
1993-03-25 発行
東辻 浩夫
Department of ElectricaJ and Electronic Engineering
Numerical simulations of a single layer recurrent neural network model in which the synaptic connection matrix is formed by summing cyclic products of succesive patterns show that complex dynamics can occur with the reduction of a connectivity parameter which is the number of connection between neurons. The structure in these dynamics is discussed from the viewpoint of realizing complex function using complex dynamics.