MétaCan
← all works

Human-level concept learning through probabilistic program induction

2015· article· en· 2,930 citations· W2194321275 on OpenAlex· 10.1126/science.aab3050

Why is this work in the frame?

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

Canadian affiliationAn author listed a Canadian institution. This is the only route the usual frame has.
Canadian funderA Canadian agency funded it. The work may carry no Canadian affiliation at all.

Abstract

People learning new concepts can often generalize successfully from just a single example, yet machine learning algorithms typically require tens or hundreds of examples to perform with similar accuracy. People can also use learned concepts in richer ways than conventional algorithms-for action, imagination, and explanation. We present a computational model that captures these human learning abilities for a large class of simple visual concepts: handwritten characters from the world's alphabets. The model represents concepts as simple programs that best explain observed examples under a Bayesian criterion. On a challenging one-shot classification task, the model achieves human-level performance while outperforming recent deep learning approaches. We also present several "visual Turing tests" probing the model's creative generalization abilities, which in many cases are indistinguishable from human behavior.

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.

The record

Venue
Science
Topic
Machine Learning and Algorithms
Field
Computer Science
Canadian institutions
Canada Research ChairsUniversity of Toronto
Funders
Army Research OfficeOffice of Naval ResearchNatural Sciences and Engineering Research Council of CanadaCanadian Institute for Advanced Research
Keywords
Computer scienceAlphabetArtificial intelligenceProbabilistic logicTuringNatural language processingMachine learningProgramming languageLinguistics
Has abstract in OpenAlex
yes