Hill Climb Modular Assembler Encoding: Evolving Modular Neural Networks of fixed modular architecture

作者：

Highlights：

• HCMAE: A new method for evolving modular neural networks.

• HCMAE was tested on two well-known benchmarks, for four different modular neural architectures.

• HCMAE outperforms Differential Evolution and Particle Swarm Optimization.

摘要

•HCMAE: A new method for evolving modular neural networks.•HCMAE was tested on two well-known benchmarks, for four different modular neural architectures.•HCMAE outperforms Differential Evolution and Particle Swarm Optimization.

论文关键词：Neuro-evolution,Modular neural networks,Two-spiral problem,Inverted-pendulum problem

论文评审过程：Received 12 October 2020, Revised 15 July 2021, Accepted 10 September 2021, Available online 14 September 2021, Version of Record 24 September 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107493