MétaCan
Menu
Back to cohort
Record W2963096987

A closer look at memorization in deep networks

2017· article· en· W2963096987 on OpenAlexafffund
Devansh Arpit, Stanisław Jastrzȩbski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, Simon Lacoste-Julien

Bibliographic record

VenueJagiellonian University Repository (Jagiellonian University) · 2017
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsPolytechnique MontréalCanadian Institute for Advanced ResearchMcGill UniversityUniversité de MontréalConcordia University
FundersSamsungInstitut de Valorisation des DonnéesNatural Sciences and Engineering Research Council of CanadaSamsung Advanced Institute of TechnologyCanadian Institute for Advanced Research
KeywordsMemorizationDeep neural networksComputer scienceArtificial intelligenceGeneralizationDeep learningRobustness (evolution)Regularization (linguistics)Artificial neural networkMachine learningAdversarial systemNoise (video)MathematicsCognitive psychologyPsychology
DOInot available

Abstract

fetched live from OpenAlex

We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness.While deep networks are capable of memorizing noise data, our results suggest that they tend to prioritize learning simple patterns first.In our experiments, we expose qualitative differences in gradient-based optimization of deep neural networks (DNNs) on noise vs. real data.We also demonstrate that for appropriately tuned explicit regularization (e.g., dropout) we can degrade DNN training performance on noise datasets without compromising generalization on real data.Our analysis suggests that the notions of effective capacity which are dataset independent are unlikely to explain the generalization performance of deep networks when trained with gradient based methods because training data itself plays an important role in determining the degree of memorization.

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.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.019
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.005
Threshold uncertainty score0.016

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.019
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.004
Scholarly communication0.0020.009
Open science0.0020.003
Research integrity0.0010.004
Insufficient payload (model declined to judge)0.0050.000

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 head0.006
GPT teacher head0.188
Teacher spread0.182 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations654
Published2017
Admission routes2
Has abstractyes

Explore more

Same venueJagiellonian University Repository (Jagiellonian University)Same topicAdversarial Robustness in Machine LearningFrench-language works237,207