Improving the performance of mutation-based evolving artificial neural networks with self-adaptive mutations.

Autor: Hiraga M; Faculty of Mechanical Engineering, Kyoto Institute of Technology, Kyoto, Japan., Komura M; Graduate School of Advanced Science and Engineering, Hiroshima University, Hiroshima, Japan., Miyamoto A; Graduate School of Advanced Science and Engineering, Hiroshima University, Hiroshima, Japan., Morimoto D; Department of Mechanical and Control Engineering, Kyushu Institute of Technology, Fukuoka, Japan., Ohkura K; Graduate School of Advanced Science and Engineering, Hiroshima University, Hiroshima, Japan.
Jazyk: angličtina
Zdroj: PloS one [PLoS One] 2024 Jul 15; Vol. 19 (7), pp. e0307084. Date of Electronic Publication: 2024 Jul 15 (Print Publication: 2024).
DOI: 10.1371/journal.pone.0307084
Abstrakt: Neuroevolution is a promising approach for designing artificial neural networks using an evolutionary algorithm. Unlike recent trending methods that rely on gradient-based algorithms, neuroevolution can simultaneously evolve the topology and weights of neural networks. In neuroevolution with topological evolution, handling crossover is challenging because of the competing conventions problem. Mutation-based evolving artificial neural network is an alternative topology and weights neuroevolution approach that omits crossover and uses only mutations for genetic variation. This study enhances the performance of mutation-based evolving artificial neural network in two ways. First, the mutation step size controlling the magnitude of the parameter perturbation is automatically adjusted by a self-adaptive mutation mechanism, enabling a balance between exploration and exploitation during the evolution process. Second, the structural mutation probabilities are automatically adjusted depending on the network size, preventing excessive expansion of the topology. The proposed methods are compared with conventional neuroevolution algorithms using locomotion tasks provided in the OpenAI Gym benchmarks. The results demonstrate that the proposed methods with the self-adaptive mutation mechanism can achieve better performance. In addition, the adjustment of structural mutation probabilities can mitigate topological bloat while maintaining performance.
Competing Interests: The authors have declared that no competing interests exist.
(Copyright: © 2024 Hiraga et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje