Learning of neural networks approximating continuous functions through circuit simulator SPICE-PAC driven by simulated annealing

Simulated annealing (SA) adapted to continuous variables is used lo determine the synaptic coefficients of an analogue multilayer neural network, approximating any continuous function of one or several variables. The ‘open’ electrical simulator SPICE-PAC driven by SA 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 simple examples.