MétaCan
Menu
Back to cohort
Record W4398184421 · doi:10.1609/aaaiss.v3i1.31276

Pushing the Limits of Learning from Limited Data

2024· article· en· W4398184421 on OpenAlexfundno aff
Maya Malaviya, Ilia Sucholutsky, Thomas L. Griffiths

Bibliographic record

VenueProceedings of the AAAI Symposium Series · 2024
Typearticle
Languageen
FieldComputer Science
TopicDigital Imaging for Blood Diseases
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of CanadaNOMIS Stiftung
KeywordsMechanism (biology)Process (computing)Limit (mathematics)Computer scienceData scienceCognitive psychologyPsychologyArtificial intelligenceEpistemologyMathematics

Abstract

fetched live from OpenAlex

What is the mechanism behind people's remarkable ability to learn from very little data, and what are its limits? Preliminary evidence suggests people can infer categories from extremely sparse data, even when they have fewer labeled examples than categories. However, the mechanisms behind this learning process are unclear. In our experiment, people learned 8 categories defined over a 2D manifold from just 4 labeled examples. Our results suggest that people are forming rich representations of the underlying categories despite this limited information. These results push the limits of how little information people need to build strong and systematic category representations.

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 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: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.238
Threshold uncertainty score0.960

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 communication0.0010.004
Open science0.0040.002
Research integrity0.0000.000
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 head0.030
GPT teacher head0.247
Teacher spread0.217 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
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

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueProceedings of the AAAI Symposium SeriesSame topicDigital Imaging for Blood DiseasesFrench-language works237,207