A hybrid MPSO-BP structure adaptive algorithm for RBFNs

Abstract

This paper introduces a novel hybrid algorithm to determine the parameters of radial basis function neural networks (number of neurons, centers, width and weights) automatically. The hybrid algorithm combines the mix encoding particle swarm optimization algorithm with the back propagation (BP) algorithm to form a hybrid learning algorithm (MPSO-BP) for training Radial Basis Function Networks (RBFNs), which adapts to the network structure and updates its weights by choosing a special fitness function. The proposed method is used to deal with three nonlinear problems, and the results obtained are compared with existent bibliography, showing an improvement over the published methods.

A Decision Model for Bike Sharing Based on Big Data Analysis

“…The typical structure of the BPNN includes an input layer, a hidden layer, and an output layer. Each layer has a certain number of nodes [15]. This structure was adopted for our research, for one hidden layer is sufficient to realize all kinds of nonlinear mappings.…”

Data processing with an Improved Hybrid Optimization Algorithm Base on PSO-GA

“…New hybrid PSO-GA algorithm. We developed an effective hybrid optimization algorithm based on PSO and GA. First, the population is evolved over a certain number of generations by PSO and the best M particles are retained; the remaining , go to step (5), otherwise go to step ( 14). ( 5) Let…”

“…The GA developed by Holland is based on the Darwinian theory of biological evolution [1] . It has been a very important stochastic search algorithm for solving optimization problems during the last two decades, including operations research, image processing, and control problems [2][3][4][5] . However, the drawback of GA is that, because of its stochastic nature, it is not possible to predict the required number of generations for obtaining a solution to within a certain level of accuracy, which can result in an excessive computational burden [6] .…”