SA-Prop: Optimization of Multilayer Perceptron Parameters Using Simulated Annealing

摘要

A general problem in model selection is to obtain the right parameters that make a model fit observed data. If the model selected is a Multilayer Perceptron (MLP) trained with Backpropagation (BP), it is necessary to find appropriate initial wights and learning parameters. This paper proposes a method that combines Simulated annealing (SinAnn) and BP to train MLPs with a single hidden layer, termed SA-Prop. SimAnn selects the initial weights and the learning rate of the network. SA-Prop combines the advantages of the stochastic search performed by the Simulated Annealing over the MLP parameter space and the local search ofthe BP algorithm.