Global Stability of a Hebbian/Anti-Hebbian Network for Principal Subspace Learning
Neural Computation · 02.06.2026 · 38 (7) · 1180-1202
DOI: 10.1162/neco.a.1524 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Computation, online erschienen am 02.06.2026. Verfasst von David Lipshutz und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neuroscience, Baylor College of Medicine, Houston, TX 77030, USA. Hauptthemen laut MEDLINE: Neural Networks, Computer, Models, Neurological, Learning. Die Arbeit nennt 28 Literaturangaben.
Abstract (Originalsprache)
Biological neural networks self-organize according to local synaptic modifications to produce stable computations. How modifications at the synaptic level give rise to such computations at the network level remains an open question. Pehlevan et al. (2015) proposed a model of a self-organizing neural network with Hebbian and anti-Hebbian synaptic updates that implements an algorithm for principal subspace analysis; however, global stability of the nonlinear synaptic dynamics has not been established. Here, for the case that the feedforward and recurrent weights evolve at the same timescale, we prove global stability of the continuum limit of the synaptic dynamics and show that the dynamics evolve in two phases. In the first phase, the synaptic weights converge to an invariant manifold where the neural filters are orthonormal. In the second phase, the synaptic dynamics follow the gradient flow of a nonconvex potential function whose minima correspond to neural filters that span the principal subspace of the input data.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Neuroscience, Baylor College of Medicine, Houston, TX 77030, USA.
- Neuroengineering Initiative, Rice University, Houston, TX 77030, USA david.lipshutz@bcm.edu.
- Independent researcher, Palo Alto, CA 94301, USA roblipshutz@gmail.com.
Zitieren
APA
Lipshutz, D., & Lipshutz, R. J. (2026). Global Stability of a Hebbian/Anti-Hebbian Network for Principal Subspace Learning. Neural Computation, 38(7), 1180-1202. https://doi.org/10.1162/neco.a.1524
Vancouver
Lipshutz D, Lipshutz RJ. Global Stability of a Hebbian/Anti-Hebbian Network for Principal Subspace Learning. Neural Computation. 2026;38(7):1180-1202. doi:10.1162/neco.a.1524
BibTeX
@article{Lipshutz2026,
author = {Lipshutz, David and Lipshutz, Robert J},
title = {Global Stability of a Hebbian/Anti-Hebbian Network for Principal Subspace Learning},
journal = {Neural Computation},
year = {2026},
volume = {38},
number = {7},
pages = {1180--1202},
doi = {10.1162/neco.a.1524}
}
EUVIMED