Kernel Logistic Regression Learning for High-Capacity Hopfield Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Tamamori, Akira
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911004290449408
author Tamamori, Akira
author_facet Tamamori, Akira
contents Hebbian learning limits Hopfield network storage capacity (pattern-to-neuron ratio around 0.14). We propose Kernel Logistic Regression (KLR) learning. Unlike linear methods, KLR uses kernels to implicitly map patterns to high-dimensional feature space, enhancing separability. By learning dual variables, KLR dramatically improves storage capacity, achieving perfect recall even when pattern numbers exceed neuron numbers (up to ratio 1.5 shown), and enhances noise robustness. KLR demonstrably outperforms Hebbian and linear logistic regression approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2504_07633
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Kernel Logistic Regression Learning for High-Capacity Hopfield Networks
Tamamori, Akira
Machine Learning
Neural and Evolutionary Computing
Hebbian learning limits Hopfield network storage capacity (pattern-to-neuron ratio around 0.14). We propose Kernel Logistic Regression (KLR) learning. Unlike linear methods, KLR uses kernels to implicitly map patterns to high-dimensional feature space, enhancing separability. By learning dual variables, KLR dramatically improves storage capacity, achieving perfect recall even when pattern numbers exceed neuron numbers (up to ratio 1.5 shown), and enhances noise robustness. KLR demonstrably outperforms Hebbian and linear logistic regression approaches.
title Kernel Logistic Regression Learning for High-Capacity Hopfield Networks
topic Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2504.07633