Online learning of neural networks based on a model-free control algorithm

Abstract

We explore the possibilities of using a model-free-based control law in order to train artificial neural networks. In the supervised learning context, we consider the problem of tuning the synaptic weights as a feedback control tracking problem where the control algorithm adjusts the weights online according to the input-output training data set of the neural network. Numerical results illustrate the dynamical learning process and an example of classifier that show very promising properties of our proposed approach.

arXiv comment8 pages, 4 figures, Accepted to the APMS 2021 conference