A Markovian study of recurrent neural networks with stochastic dynamics
Daniela Zaharie · 1996
Recurrent neural networks of binary stochastic units with a general dis tribution function are studied using Markov chains theory. Sufficient conditions for ergodicity are established and under some assumptions, the stationary distribution is determined. The relation between fixed points and absorbing states is studied both theo retically and through simulations. For numerical studies the notion of almost absorbing state is introduced.