Targeting Spatio–Temporal Patterns in Chaotic Neural Network
Manish Dev Shrimali, HE Guo-guang, Kazuyuki Aihara · 2007
Abstract We have studied the chaos control in chaotic neural network by limiting the phase space at varying time interval. It provides a controlled output patterns with different temporal periods depending upon the control parameters. The chaotic neural network constructed with chaotic neurons exhibits very rich dynamic behavior with a non–periodic associative memory. In the chaotic neural network, it is difficult to distinguish the stored patterns from others, because of the chaotic states of output of the network. In order to apply the non–periodic associative memory into information search and pattern identification, etc, it is necessary to control chaos in this chaotic neural network.