AN ASSOCIATION OF SIMULATED ANNEALING AND ANALOG NEURAL NETWORKS ELECTRICAL SIMULATOR SPICE-PAC FOR LEARNING OF

Simulated Annealing adapted to continuous variables is used to determine the synaptic coefficients of an analog multilayer neural network, approximating any continuous function of one or several variables. The “open” electrical simulator SPICEPAC driven by Simulated Annealing produces a globally optimal set of synaptic weights, in a reasonable time and without requiring heavy and inaccurate gradient computations. We illustrate and improve our weights tuning strategy through two simple examples.