Hugging Face Trending Papers
Phases in a class of associative memories via hidden neurons
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Machine Learning
Sep 11
Phases in a class of associative memories via hidden neurons
The paper investigates associative memory in a bipartite Hopfield–Krotov architecture, termed class H, where hidden neurons serve as the retrieval order parameter. Using the replica method, it derives replica‑symmetric phase diagrams and closed‑form capacities for polynomial load, showing that crosstalk statistics are similar for Ising and spherical visible neurons. With a softmax hidden layer, the load becomes exponential, mapping the thermodynamics onto a random‑energy‑model that exhibits paramagnetic, condensed, and frozen phases, and revealing that heating destabilizes retrieval through quantized attention reassignments while Gaussian patterns remain metastable at all loads.
arXiv AI
Jul 22
Free energy landscape of Dense Associative Memory
arXiv:2607. 19195v1 Announce Type: cross Abstract: Using large deviations theory, we solve and obtain a general expression for the free energy functional for a broad class of associative memories, including dense associative memories.
arXiv Machine Learning
Jul 2
Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networks
arXiv:2605. 00366v4 Announce Type: replace-cross Abstract: High-capacity associative memories based on Kernel Logistic Regression (KLR) exhibit strong storage capabilities, but the dynamical and geometric mechanisms underlying their stability remain poorly understood.
arXiv Machine Learning
Jul 14
Redundancy Maximization as a Principle of Associative Memory Learning in Hopfield Networks
arXiv:2511. 02584v2 Announce Type: replace-cross Abstract: Associative memory, traditionally modeled by Hopfield networks, enables the retrieval of previously stored patterns from partial or noisy cues.
arXiv Machine Learning
5d ago
On associative neural networks for sparse patterns with huge capacities
arXiv:2603. 26217v2 Announce Type: replace-cross Abstract: Generalized Hopfield models with higher-order or exponential interaction terms are known to have substantially larger storage capacities than the classical quadratic model.
arXiv Machine Learning
Sep 15
Random matrix theory of sparse neuronal networks with heterogeneous timescales
arXiv:2512.12767v2 Announce Type: replace-cross Abstract: Training recurrent neuronal networks consisting of excitatory (E) and inhibitory (I) units with additive noise for working memory computation...