Statistical physics, Bayesian inference and neural information processing

Berfin \c{S}im\c{s}ek; Erin Grant; Sandra Nestler; Sara Solla

Statistical physics, Bayesian inference and neural information processing

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2309.17006 v1 pith:W6YTODL5 submitted 2023-09-29 cond-mat.dis-nn stat.ML

Erin Grant , Sandra Nestler , Berfin Şimşek , Sara Solla This is my paper

classification cond-mat.dis-nnstat.ML

keywords physicsstatisticalbayesianinferenceinformationlearninglinearneural

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

Lecture notes from the course given by Professor Sara A. Solla at the Les Houches summer school on "Statistical physics of Machine Learning". The notes discuss neural information processing through the lens of Statistical Physics. Contents include Bayesian inference and its connection to a Gibbs description of learning and generalization, Generalized Linear Models as a controlled alternative to backpropagation through time, and linear and non-linear techniques for dimensionality reduction.

Discussion (0). Sign in 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

SETOL: A Semi-Empirical Theory of (Deep) Learning
cs.LG 2025-07 conditional novelty 7.0 of 10

SETOL derives the HTSR layer quality metrics as integrated R-transforms of the layer spectral density, and proposes a determinant condition (ERG) as a marker of ideal learning.

Pith tools