Memory of Square Wave Signals in the Time Delay Neural Networks
Liang-Ming He · 2005
The role that different square wave signals play in the dynamics of a time delay network of McCulloch-Pitts elements have been investigated using computer simulations. The different cycle (positive and negative) square wave signals induce the following network features: signals, whose cycles exactly divide the delay time, give rise to system memory; on the other hand, signals, whose cycles have not the numerical relationship mentioned above with or are larger than the delay time, give rise to disordered integral activity of the network or patterns which can not exhibit step of the inputs after the inputs are eliminated. This phenomenon is analyses by means of the degree of synchronization.