Training Product Units in Feedforward Neural Networks using Particle Swarm Optimization

A Ismail, AP Engelbrecht

Abstract

Product unit (PU) neural networks are powerful because of their ability to handle higher order combinations of inputs. Training of PUs by backpropagation is however difficult, because of the introduction of more local minima. This paper compares training of a product unit neural network using particle swarm optimization with training of a PU using gradient descent.