We present results for the determination of the equilibrium microstate probability distribution of a class of strongly interacting systems obeying stochastic dynamics but without the necessity of detailed balance. The specific case of Ising systems is highlighted, with applications to...

We consider training noise in neural networks as a means of tuning the structure of retrieval basins, and study how learning and retrieving properties depend on it. The stability of the replica symmetric solution and the correlation in the weight space indicate that neural networks can be...

We apply the principle of adaptation to optimize the performance of neural networks with (i) noisy retrieval and (ii) disruptive dilution.

We consider a neural network model which exhibits novel behaviours in sequential learning other than simple primacy and recency effects.