An Improved Evolutionary Random Neural Networks Based on Particle Swarm Optimization and Input-to-Output Sensitivity

Abstract

Extreme learning machine (ELM) for random single-hidden-layer feedforward neural networks (SLFN) has been widely applied in many fields because of its fast learning speed and good generalization performance. Since ELM randomly selects the input weights and hidden biases, it typically requires high number of hidden neurons and thus decreases its convergence performance. To overcome the deficiency of the traditional ELM, an improved ELM based on particle swarm optimization (PSO) and input-to-output sensitivity information is proposed in this study. In the improved ELM, PSO encoding the input-to-output sensitivity information of the SLFN is used to optimize the input weights and hidden biases. The improved ELM could obtain better generalization performance and improve the conditioning of the SLFN by decreasing the input-to-output sensitivity of the network. Experiment results on the classification problems verify the improved performance of the proposed ELM.