Pith. sign in

REVIEW 1 cited by

Stochastic Thermodynamics of Learning

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 1611.09428 v1 pith:2NIJWMAX submitted 2016-11-28 cond-mat.stat-mech cond-mat.dis-nnphysics.bio-ph

classification cond-mat.stat-mechcond-mat.dis-nnphysics.bio-ph
keywords learninganalyseinformationnetworkneuralstochasticthermodynamicthermodynamics
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Virtually every organism gathers information about its noisy environment and builds models from that data, mostly using neural networks. Here, we use stochastic thermodynamics to analyse the learning of a classification rule by a neural network. We show that the information acquired by the network is bounded by the thermodynamic cost of learning and introduce a learning efficiency $\eta\le1$. We discuss the conditions for optimal learning and analyse Hebbian learning in the thermodynamic limit.

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. Thermodynamics of Learning: A Typed Four-Component Accounting of Memory, Fit, and Value

    cond-mat.stat-mech 2026-08 conditional novelty 7.0 of 10

    A typed accounting separates record correlation from operational capital value in finite learning devices, with separation, capitalization-efficiency, and value-retention theorems.

Pith tools