CONSTRAINED WEIGHT INFERENCE FOR ONLINE DISTRIBUTED LEARNING

A computer system comprising an artificial neural network comprising a plurality of units to learn a certain task, wherein the units are directionally connected and the network as a whole is organized to generate an output based on an input. The neural network is configured to calculate (303) an internal state value for each unit of the neural network, based on output values of the other units of the neural, weights associated with the directional connections in the neural network acting between pairs of units, and a perturbation value associated with each unit of the neural network, wherein the output value of a subset of units of the network corresponds to an input value of the neural network and the output values of a different subset of units comprise the output of the neural network.