A Differential Manifold Perspective and Universality Analysis of Continuous Attractors in Artificial Neural Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tian, Shaoxin, Liu, Hongkai, Yang, Yuying, Yu, Jiali, Miao, Zizheng, Huang, Xuming, Liu, Zhishuai, Yi, Zhang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918140382806016
author Tian, Shaoxin
Liu, Hongkai
Yang, Yuying
Yu, Jiali
Miao, Zizheng
Huang, Xuming
Liu, Zhishuai
Yi, Zhang
author_facet Tian, Shaoxin
Liu, Hongkai
Yang, Yuying
Yu, Jiali
Miao, Zizheng
Huang, Xuming
Liu, Zhishuai
Yi, Zhang
contents Continuous attractors are critical for information processing in both biological and artificial neural systems, with implications for spatial navigation, memory, and deep learning optimization. However, existing research lacks a unified framework to analyze their properties across diverse dynamical systems, limiting cross-architectural generalizability. This study establishes a novel framework from the perspective of differential manifolds to investigate continuous attractors in artificial neural networks. It verifies compatibility with prior conclusions, elucidates links between continuous attractor phenomena and eigenvalues of the local Jacobian matrix, and demonstrates the universality of singular value stratification in common classification models and datasets. These findings suggest continuous attractors may be ubiquitous in general neural networks, highlighting the need for a general theory, with the proposed framework offering a promising foundation given the close mathematical connection between eigenvalues and singular values.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10514
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Differential Manifold Perspective and Universality Analysis of Continuous Attractors in Artificial Neural Networks
Tian, Shaoxin
Liu, Hongkai
Yang, Yuying
Yu, Jiali
Miao, Zizheng
Huang, Xuming
Liu, Zhishuai
Yi, Zhang
Machine Learning
Continuous attractors are critical for information processing in both biological and artificial neural systems, with implications for spatial navigation, memory, and deep learning optimization. However, existing research lacks a unified framework to analyze their properties across diverse dynamical systems, limiting cross-architectural generalizability. This study establishes a novel framework from the perspective of differential manifolds to investigate continuous attractors in artificial neural networks. It verifies compatibility with prior conclusions, elucidates links between continuous attractor phenomena and eigenvalues of the local Jacobian matrix, and demonstrates the universality of singular value stratification in common classification models and datasets. These findings suggest continuous attractors may be ubiquitous in general neural networks, highlighting the need for a general theory, with the proposed framework offering a promising foundation given the close mathematical connection between eigenvalues and singular values.
title A Differential Manifold Perspective and Universality Analysis of Continuous Attractors in Artificial Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2509.10514