arXiv:2504.07633cs.LGcs.NE2025-04中稿 · IEICE Transactions…被引 7

用核逻辑回归提升霍普菲尔德网络存储能力,突破传统极限

Kernel Logistic Regression Learning for High-Capacity Hopfield Networks

  • 引入核逻辑回归,将模式映射到高维特征空间增强可分性
  • 存储容量比达1.5(模式数超神经元数),实现完美召回
  • 适合需要高容量存储与抗噪的神经网络应用

海布学习限制了霍普菲尔德网络的存储容量(模式-神经元比约0.14)。本文提出核逻辑回归(KLR)学习方法。与线性方法不同,KLR通过核函数隐式将模式映射至高维特征空间,提升模式可分性。通过学习对偶变量,KLR显著提升存储容量,在模式数量超过神经元数量时仍能实现完美召回(最高比率达1.5),并增强抗噪能力。实验表明,KLR明显优于海布学习和线性逻辑回归方法。

原文摘要 · Abstract (English)

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.

霍普菲尔德网络核方法存储容量

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。