Towards a model of visual reasoning

Ekaterina Shurkova, Leonidas A A Doumas

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

Abstract

Many tasks that are easy for humans are difficult for machines. Particularly, while humans excel at tasks that require generalising across problems, machine systems notably struggle. One such task is the Synthetic Visual Reasoning Test (SVRT). The SVRT consists of a range of problems where simple visual stimuli must be categorised into one of two categories based on an unknown rule that must be induced. Conventional machine learning approaches perform well only when trained to categorise based on a single rule and are unable to generalise without extensive additional training to tasks with any additional rules. Multiple theories of higher-level cognition posit that humans solve such tasks using structured relational representations. Specifically, people learn rules based on structured representations that generalise to novel instances quickly and easily. We believe it is possible to model this approach in a single system which learns all the required relational representations from scratch and performs tasks such as SVRT in a single run. Here, we present a system which expands the DORA/LISA architecture and augments the existing model with principally novel components, namely a) visual reasoning based on the established theories of recognition by components; b) the process of learning complex relational representations by synthesis (in addition to learning by analysis). The proposed augmented model matches human behaviour on SVRT problems. Moreover, the proposed system stands as a more realistic account of human cognition, wherein rather than using tools that have been shown successful in the machine learning field to inform psychological theorising, we use established psychological theories to inform developing a machine system.
Original languageEnglish
Title of host publicationProceedings of the 44th Annual Conference of the Cognitive Science Society
EditorsJennifer Culbertson, Andrew Perfors, Hugh Rabagliati, Veronica Ramenzoni
PublishereScholarship University of California
Pages1204-1210
Publication statusE-pub ahead of print - 17 Jun 2022
Event44th Annual Meeting of the Cognitive Science Society - Toronto, Canada
Duration: 27 Jul 202230 Jul 2022
Conference number: 44
https://cognitivesciencesociety.org/cogsci-2022/

Publication series

NameProceedings of the Annual Conference of the Cognitive Science Society
PublisherCognitive Science Society
Volume44
ISSN (Electronic)1069-7977

Conference

Conference44th Annual Meeting of the Cognitive Science Society
Abbreviated titleCogSci 2022
Country/TerritoryCanada
CityToronto
Period27/07/2230/07/22
Internet address

Keywords

  • visual reasoning
  • visual tasks
  • relational reasoning
  • symbolic-connectionist model

Fingerprint

Dive into the research topics of 'Towards a model of visual reasoning'. Together they form a unique fingerprint.

Cite this