MétaCan
Menu
Back to cohort
Record W2160725942

The Consolidation of Task Knowledge for Lifelong Machine Learning

2013· article· en· W2160725942 on OpenAlexaff
Daniel Silver

Bibliographic record

VenueNational Conference on Artificial Intelligence · 2013
Typearticle
Languageen
FieldComputer Science
TopicDomain Adaptation and Few-Shot Learning
Canadian institutionsAcadia University
Fundersnot available
KeywordsComputer scienceLifelong learningTask (project management)Consolidation (business)Domain knowledgeKnowledge transferKnowledge managementArtificial intelligenceHuman–computer interactionEngineeringPsychologySystems engineering
DOInot available

Abstract

fetched live from OpenAlex

Lifelong Machine Learning (LML) considers situations in which a learner faces a series of tasks over a lifetime. An LML system requires a method of using prior knowledge to learn models for new tasks as efficiently and effectively as possible, and a method of retaining task knowledge after it has been learned. Knowledge retention is necessary for a lifelong learning system, however it is not sufficient. We propose that domain knowledge must be integrated for the purposes of efficient and effective retention and for more efficient and effective transfer during future learning. The process of integration we define as consolidation. The challenge for an LML system is consolidating the knowledge of a new task while maintaining and possibly improving knowledge of prior tasks; this requires a solution to the stability-plasticity problem. This paper provides a summary of prior work by the author on the consolidation problem within various LML systems.

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)0.004
metaresearch head score (Gemma)0.024
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 score0.004
Threshold uncertainty score0.023

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.024
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.003
Scholarly communication0.0030.009
Open science0.0030.006
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0030.001

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 head0.120
GPT teacher head0.347
Teacher spread0.227 · 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

Citations3
Published2013
Admission routes1
Has abstractyes

Explore more

Same venueNational Conference on Artificial IntelligenceSame topicDomain Adaptation and Few-Shot LearningFrench-language works237,207