An improved extreme learning machine based on Variable-length Particle Swarm Optimization

Abstract

Extreme LearningMachine (ELM) for Single-hidden Layer Feedforward Neural Network (SLFN) has been attracting attentions because of its faster learning speed and better generalization performance than those of the traditional gradient-based learning algorithms. However, it has been proven that generalization performance of ELM classifier depends critically on the number of hidden neurons and the random determination of the input weights and hidden biases. In this paper, we propose Variable-length Particle Swarm Optimization algorithm (VPSO) for ELM to automatically select the number of hidden neurons as well as corresponding input weights and hidden biases for maximizing ELM classifier's generalization performance. Experimental results have verified that the proposed VPSO-ELM scheme significantly improves the testing accuracy of classification problems.

Path-Planning for Mobile Robots Using a Novel Variable-Length Differential Evolution Variant

“…It uses a fixed-length vector with binary encoding and a range of variable values to represent a disabled state of a layer. On the other hand, the work published in [54] uses PSO to automatically select the number of hidden neurons, the input weights and the hidden biases in a single hidden layer feedforward. A stochastic strategy was proposed to update particle sizes and apply the original PSO operators over actual variable-length solutions to achieve it.…”