Hardware In-the-Loop Training of Analogue Neural Network Chip.

In this paper we present the results of neural network hardware in-the-loop training for an analogue Local Cluster Neural Network (LCNN) chip. We use a Probabilistic Random Weight Change (PRWC) algorithm that is a combination of the random weight change and simulated annealing algorithms. We applied the PRWC algorithm to in-the-loop training for multi-dimensional function approximations and for predictions. We discuss the training strategy and the experiment results. [ABSTRACT FROM AUTHOR]