Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models

Hopfield network
DOI: 10.48550/arxiv.2404.03827 Publication Date: 2024-04-04
ABSTRACT
We propose a two-stage memory retrieval dynamics for modern Hopfield models, termed $\mathtt{U\text{-}Hop}$, with enhanced capacity. Our key contribution is learnable feature map $\Phi$ which transforms the energy function into kernel space. This transformation ensures convergence between local minima of and fixed points within Consequently, norm induced by serves as novel similarity measure. It utilizes stored patterns learning data to enhance capacity across all models. Specifically, we accomplish this constructing separation loss $\mathcal{L}_\Phi$ that separates kernelized separating in Methodologically, $\mathtt{U\text{-}Hop}$ process consists of: \textbf{(Stage~I.)} minimizing more uniformed (local minimum) distribution, followed \textbf{(Stage~II.)} standard minimization retrieval. results significant reduction possible meta-stable states function, thus enhancing preventing confusion. Empirically, real-world datasets, demonstrate outperforms existing models SOTA measures, achieving substantial improvements both associative deep tasks.
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES ()
CITATIONS ()
EXTERNAL LINKS
PlumX Metrics
RECOMMENDATIONS
FAIR ASSESSMENT
Coming soon ....
JUPYTER LAB
Coming soon ....