Grounding compositional hypothesis generation in specific instances

Neil Bramley, Anselm Rothe, Joshua B. Tenenbaum, Fei Xu, Todd Gureckis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

A number of recent computational models treat concept learning as a form of probabilistic rule induction in a space of language-like, compositional concepts. Inference in such models frequently requires repeatedly sampling from a (infinite) distribution over possible concept rules and comparing their relative likelihood in light of current data or evidence. However, we argue that most existing algorithms for top-down sampling are inefficient and cognitively implausible accounts of human hypothesis generation. As a result, we propose an alternative, Instance Driven Generator (IDG), that constructs bottom-up hypotheses directly out of encountered positive instances of a concept. Using a novel rule induction task based on the children’s game Zendo, we compare these “bottom-up” and “top-down” approaches to inference. We find that the bottom-up IDG model accounts better for human inferences and results in a computationally more tractable inference mechanism for concept learning models based on a probabilistic language of thought.
Original languageEnglish
Title of host publicationProceedings of the 40th Annual Conference of the Cognitive Science Society
Place of PublicationAustin, TX
PublisherCognitive Science Society
ISBN (Print)9780991196784
Publication statusPublished - 31 Dec 2018
Event40th Annual Meeting of the Cognitive Science Society - Madison, United States
Duration: 25 Jul 201828 Jul 2018


Conference40th Annual Meeting of the Cognitive Science Society
Abbreviated titleCogSci 2018
Country/TerritoryUnited States
Internet address

Keywords / Materials (for Non-textual outputs)

  • discovery
  • program induction
  • robabilistic lan-guage of thought
  • active learning
  • hypothesis generation


Dive into the research topics of 'Grounding compositional hypothesis generation in specific instances'. Together they form a unique fingerprint.

Cite this