Nonsmooth Optimisation and neural networks

Abstract

In this paper, we study neural networks from the point of view of nonsmooth optimisation, namely, quasidifferential calculus. We restrict ourselves to the case of uniform approximation by a neural network without hidden layers, the activation functions are restricted to continuous strictly increasing functions. We develop an algorithm for computing the approximation with one hidden layer through a step-by-step procedure. The nonsmooth analysis techniques demonstrated their efficiency. In particular, they partially explain why the developed step-by-step procedure may run without any objective function improvement after just one step of the procedure.