An improved artificial neural network based on human-behaviour particle swarm optimization and cellular automata

作者：

Highlights：

• A local version of HPSO with CA is proposed to improve convergence performance.

• HPSO-CA is combined with ANN to prevent ANN from trapping in local minima.

• ANN-HPSO-CA is proved to be effective to train ANN’s connectivity weights.

• The proposed ANN-HPSO-CA shows a competitive performance on the tested datasets.

摘要

•A local version of HPSO with CA is proposed to improve convergence performance.•HPSO-CA is combined with ANN to prevent ANN from trapping in local minima.•ANN-HPSO-CA is proved to be effective to train ANN’s connectivity weights.•The proposed ANN-HPSO-CA shows a competitive performance on the tested datasets.

论文关键词：Artificial neural networks,Weight training,Human behavior-based particle swarm optimization,Cellular automata,EA-based ANN models

论文评审过程：Received 27 January 2019, Revised 6 July 2019, Accepted 2 August 2019, Available online 2 August 2019, Version of Record 17 August 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112862