Kernel Hopfield networks self-organize on an optimization ridge into a critical spectral regime where the leading eigenvalue enhances stability while trailing eigenvalues sustain high capacity.
Storing infinite numbers of patterns in a spin-glass model of neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2025 2verdicts
UNVERDICTED 2representative citing papers
Simulations show that kernel regression methods achieve linear storage capacity scaling with network size in Hopfield networks when kernel width is scaled as gamma N increasing with N.
citing papers explorer
-
Self-Organization and Spectral Mechanism of Attractor Landscapes in High-Capacity Kernel Hopfield Networks
Kernel Hopfield networks self-organize on an optimization ridge into a critical spectral regime where the leading eigenvalue enhances stability while trailing eigenvalues sustain high capacity.
-
Quantitative Attractor Analysis of High-Capacity Kernel Hopfield Networks
Simulations show that kernel regression methods achieve linear storage capacity scaling with network size in Hopfield networks when kernel width is scaled as gamma N increasing with N.