The Role of Higher-Order Self-Dynamics in Neural Dynamical Networks: Preserving Memory Capacity and Enhancing Retrieval Basin
SIAM Journal on Applied Mathematics · 31.08.2025 · 85 (4) · 1834-1855
DOI: 10.1137/24m1702477 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Applied Mathematics, online erschienen am 14.08.2025. Verfasst von Weichen Fu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 26 Literaturangaben. Gefördert von: SMEC, National Natural Science Foundation of China.
Abstract (Originalsprache)
Networks of coupled Kuramoto-type oscillators have been proposed as models of associative memory. In this paper, we design a model for neural dynamical networks by incorporating higher-order self-dynamics. This system is not invariant under global phase translation, which makes it more direct to link phases and patterns. We present a unified approach for error-free retrieval in the pattern retrieval problem with an arbitrary set of standard patterns. We find that this model preserves the memory capacity, simultaneously enhancing the basin for error-free retrieval. More practically, we propose a strategy for the retrieval problems with grayscale and even colorful images.
Förderung
- SMEC
- National Natural Science Foundation of China
Zitieren
APA
Fu, W., Li, Z., Lin, W., & Zhao, X. (2025). The Role of Higher-Order Self-Dynamics in Neural Dynamical Networks: Preserving Memory Capacity and Enhancing Retrieval Basin. SIAM Journal on Applied Mathematics, 85(4), 1834-1855. https://doi.org/10.1137/24m1702477
Vancouver
Fu W, Li Z, Lin W, Zhao X. The Role of Higher-Order Self-Dynamics in Neural Dynamical Networks: Preserving Memory Capacity and Enhancing Retrieval Basin. SIAM Journal on Applied Mathematics. 2025;85(4):1834-1855. doi:10.1137/24m1702477
BibTeX
@article{Fu2025,
author = {Fu, Weichen and Li, Zhuchun and Lin, Wei and Zhao, Xiaoxue},
title = {The Role of Higher-Order Self-Dynamics in Neural Dynamical Networks: Preserving Memory Capacity and Enhancing Retrieval Basin},
journal = {SIAM Journal on Applied Mathematics},
year = {2025},
volume = {85},
number = {4},
pages = {1834--1855},
doi = {10.1137/24m1702477}
}
EUVIMED