Pith. sign in

REVIEW 1 cited by

Storage and Learning phase transitions in the Random-Features Hopfield Model

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.16880 v2 pith:KQWM2GPI submitted 2023-03-29 cond-mat.dis-nn cs.LG

classification cond-mat.dis-nncs.LG
keywords modelphaselearninghopfieldpatternsalphafeaturesmachine
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

The Hopfield model is a paradigmatic model of neural networks that has been analyzed for many decades in the statistical physics, neuroscience, and machine learning communities. Inspired by the manifold hypothesis in machine learning, we propose and investigate a generalization of the standard setting that we name Random-Features Hopfield Model. Here $P$ binary patterns of length $N$ are generated by applying to Gaussian vectors sampled in a latent space of dimension $D$ a random projection followed by a non-linearity. Using the replica method from statistical physics, we derive the phase diagram of the model in the limit $P,N,D\to\infty$ with fixed ratios $\alpha=P/N$ and $\alpha_D=D/N$. Besides the usual retrieval phase, where the patterns can be dynamically recovered from some initial corruption, we uncover a new phase where the features characterizing the projection can be recovered instead. We call this phenomena the learning phase transition, as the features are not explicitly given to the model but rather are inferred from the patterns in an unsupervised fashion.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Implicit Bias and Invariance: How Hopfield Networks Efficiently Learn Graph Orbits

    cs.LG 2025-12 conditional novelty 6.0 of 10

    Hopfield networks can memorize entire graph isomorphism classes with polynomially many samples, aided by an implicit norm-minimization bias that drives weights toward a 3-dimensional invariant subspace.

Pith tools