AGWO: Advanced GWO in multi-layer perception optimization

作者：

Highlights：

• Novel elastic, circling and attacking mechanisms are proposed in the AGWO.

• 30 benchmark functions in IEEE CEC 2014 are tested to demonstrate its advantages.

• The proposed AGWO is used to train the artificial neural network to achieve a better performance.

• The proposed AGWO is demonstrated by 7 classification and 3 function approximate datasets.

摘要

•Novel elastic, circling and attacking mechanisms are proposed in the AGWO.•30 benchmark functions in IEEE CEC 2014 are tested to demonstrate its advantages.•The proposed AGWO is used to train the artificial neural network to achieve a better performance.•The proposed AGWO is demonstrated by 7 classification and 3 function approximate datasets.

论文关键词：Multi-layer perceptron (MLP),AGWO,Neural networks,Local stagnation,Classification problem

论文评审过程：Received 6 November 2020, Revised 17 January 2021, Accepted 30 January 2021, Available online 11 February 2021, Version of Record 10 March 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114676