MétaCan
Menu
Back to cohort
Record W2949190276

On the difficulty of training Recurrent Neural Networks

2012· preprint· en· W2949190276 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) · 2012
Typepreprint
Languageen
FieldComputer Science
TopicNeural Networks and Applications
Canadian institutionsUniversité de Montréal
Fundersnot available
KeywordsConstraint (computer-aided design)Perspective (graphical)Computer scienceArtificial neural networkSimple (philosophy)Norm (philosophy)Artificial intelligenceGradient descentMathematical optimizationAlgorithmApplied mathematicsMathematicsGeometryEpistemology
DOInot available

Abstract

fetched live from OpenAlex

There are two widely known issues with prop-erly training Recurrent Neural Networks, the vanishing and the exploding gradient prob-lems detailed in Bengio et al. (1994). In this paper we attempt to improve the under-standing of the underlying issues by explor-ing these problems from an analytical, a geo-metric and a dynamical systems perspective. Our analysis is used to justify a simple yet ef-fective solution. We propose a gradient norm clipping strategy to deal with exploding gra-dients and a soft constraint for the vanishing gradients problem. We validate empirically our hypothesis and proposed solutions in the experimental section. 1.

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 categoriesnone
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 score0.574
Threshold uncertainty score0.653

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0020.001
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 head0.130
GPT teacher head0.200
Teacher spread0.071 · 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