Finite-size effects in separable recurrent neural networks
Antonio Castellanos, A C C Coolen, Laura Dalila Silva Viana · 1998
We perform a systematic analytical study of finite-size effects in separable recurrent neural network models with sequential dynamics, away from saturation. We find two types of finite-size effects: thermal fluctuations, and disorder-induced ‘frozen ’ corrections to the meanfield laws. The finite-size effects are described by equations that correspond to a time-dependent Ornstein–Uhlenbeck process. We show how the theory can be used to understand and quantify various finite-size phenomena in recurrent neural networks, with and without detailed balance.