ANALOGUE ELECTRONIC NEURAL NETWORK

The present invention concerns a method of programming an analogue electronic neural network comprising a plurality of layers of somas. Any two consecutive layers of somas are connected by a matrix of synapses. The method comprises: applying test signals to inputs of the neural network; measuring at a plurality of measurement locations in the neural network responses of at least some somas and synapses to the test signals; extracting from the neural network, based on the responses, a first parameter set characterising the behaviour of the at least some somas; carrying out a training of the neural network by applying to a training algorithm the first parameter set and training data for obtaining a second parameter set; and programming the neural network by using the second parameter set. The invention also relates to the neural network and to a method of operating it.