Hyperparameter tuning in the learning of multithreshold neurons

Abstract

The modification of the online learning algorithm for multi-valued multithreshold neurons is proposed in the paper. Conditions are stated and proved that ensure the finite successful learning. The influence of the algorithm hyperparameters on the learning process is analyzed on the base of simulation results. The recommendations are formulated concerning the choice of values of these hyperparameters, which may significantly reduce the learning time. The experiment results prove that the proposed algorithm overperforms ‘incremental’ algorithm suggested by Obradović and Parberry. Obtained results can be useful in the design of artificial neural network classifiers employing multithreshold activation functions in network nodes.