Open AccessImprove Efficiency of Extreme Learning Machine based on Chaos Particle Swarm Optimization Method
Author(s) -
Yuwen Pan Zhan Wen,
Wenzao Li Yahui Chen
Publication year - 2019
Publication title -
international journal of engineering and computer science
Language(s) - English
Resource type - Journals
ISSN - 2319-7242
DOI - 10.18535/ijecs/v8i03.4294
Subject(s) - extreme learning machine , computer science , particle swarm optimization , generalization , chaos (operating system) , algorithm , layer (electronics) , artificial intelligence , artificial neural network , mathematics , materials science , computer security , mathematical analysis , composite material
Extreme Learning Machine (ELM) and Regularized Extreme Learning Machine (RELM) have advantages of fast training speed and good generalization. However, ELM/RELM often needs numerous number of hidden layer nodes to get better performance. The superabundant nodes in hidden layer maybe lead to low running speed. Thus it is not feasible to use ELM in some fields that require high speed algorithms. Therefore, in this paper, we propose an Improved ELM/RELM Optimized based on Chaos Particle Swarm Optimization (CPSO-ELM/RELM) to reduce the number of hidden layer nodes, but still maintain a desirable accuracy. At the same time, it lowers the running speed compared with other algorithms. To verify the application of this method, we design numerous experiments for ELM and RRELM. Their simulation shows that the approach improves the speed of the algorithms, and the accuracy is still high. This makes it possible to use improved CPSO-ELM/RELM in some system with high real-time requirements.