Stochastic analysis of the dynamics of a general class of synchronous neural networks
Olivier Bernier · Journal of Physics A Mathematical and General · 1993
We present a generating-function-based method to analyse the dynamics of synchronous neural networks. It is applied to a very general model of networks of automata, which includes a certain number of neural network models of the Little type as particular cases. The method enables us to analyse the evolution of the order parameters as well as their fluctuations. These fluctuations are shown to consist of two independent parts, one due to the stochastic nature of the evolution, the other to the random nature of the stored patterns.