Dendritic Learning Empowered by Diversity-Aware Differential Evolution
IEEE Access · 2026 · 14 · 34879-34893
DOI: 10.1109/access.2026.3669958 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Zhe Xu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Jiangsu Higher Education Institutions of China, Changzhou Sci and Tech Program.
Abstract (Originalsprache)
The dendritic neuron model (DNM), inspired by the architecture of biological neurons and renowned for its superior nonlinear information processing capability, presents a promising alternative to the classical McCulloch–Pitts neuron model. However, its deployment is often constrained by the limitations of traditional backpropagation (BP), including gradient vanishing, over-reliance on gradient information, and inadequate adaptability in highly nonconvex optimization tasks. To address these issues, we propose a Diversity-Aware Differential Evolution (DADE) algorithm, a novel evolutionary learning framework for DNM training. DADE employs a population diversity–aware adaptive mutation strategy, in which the mutation factor is sampled from a Cauchy distribution, transformed via a nonlinear activation for stability, and dynamically adjusted according to real-time diversity measurements to prevent premature convergence. A refined population grouping mechanism further balances global exploration and local exploitation, while historical parameter updates enhance adaptability throughout the optimization process. Extensive experiments on diverse classification datasets demonstrate that DADE consistently outperforms BP-based training and conventional evolutionary algorithms in terms of accuracy, stability, and generalization.
Förderung
- Natural Science Foundation of Jiangsu Higher Education Institutions of China
- Changzhou Sci and Tech Program
Zitieren
APA
Xu, Z., Yang, L., Yuan, F., Zhang, B., Yu, J., & Qi, X. (2026). Dendritic Learning Empowered by Diversity-Aware Differential Evolution. IEEE Access, 14, 34879-34893. https://doi.org/10.1109/access.2026.3669958
Vancouver
Xu Z, Yang L, Yuan F, Zhang B, Yu J, Qi X. Dendritic Learning Empowered by Diversity-Aware Differential Evolution. IEEE Access. 2026;14:34879-34893. doi:10.1109/access.2026.3669958
BibTeX
@article{Xu2026,
author = {Xu, Zhe and Yang, Lin and Yuan, Fenggang and Zhang, Baohang and Yu, Jiatianyi and Qi, Xiaosha},
title = {Dendritic Learning Empowered by Diversity-Aware Differential Evolution},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {34879--34893},
doi = {10.1109/access.2026.3669958}
}
EUVIMED