MétaCan
Menu
Back to cohort
Record W3128475979 · doi:10.48550/arxiv.2101.11744

On the mapping between Hopfield networks and Restricted Boltzmann\n Machines

2021· preprint· en· W3128475979 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenuearXiv (Cornell University) · 2021
Typepreprint
Languageen
FieldComputer Science
TopicGenerative Adversarial Networks and Image Synthesis
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsBoltzmann machineHopfield networkBoltzmann constantComputer scienceRestricted Boltzmann machineArtificial intelligenceTheoretical computer scienceArtificial neural networkPhysicsThermodynamics

Abstract

fetched live from OpenAlex

Hopfield networks (HNs) and Restricted Boltzmann Machines (RBMs) are two\nimportant models at the interface of statistical physics, machine learning, and\nneuroscience. Recently, there has been interest in the relationship between HNs\nand RBMs, due to their similarity under the statistical mechanics formalism. An\nexact mapping between HNs and RBMs has been previously noted for the special\ncase of orthogonal (uncorrelated) encoded patterns. We present here an exact\nmapping in the case of correlated pattern HNs, which are more broadly\napplicable to existing datasets. Specifically, we show that any HN with $N$\nbinary variables and $p<N$ arbitrary binary patterns can be transformed into an\nRBM with $N$ binary visible variables and $p$ gaussian hidden variables. We\noutline the conditions under which the reverse mapping exists, and conduct\nexperiments on the MNIST dataset which suggest the mapping provides a useful\ninitialization to the RBM weights. We discuss extensions, the potential\nimportance of this correspondence for the training of RBMs, and for\nunderstanding the performance of deep architectures which utilize RBMs.\n

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.868
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.002
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.064
GPT teacher head0.177
Teacher spread0.113 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it