Deep Neural Networks Predict Category Typicality Ratings for Images

Brenden M. Lake, Wojciech Zaremba, Robert Fergus, Todd M. Gureckis

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

Abstract

The latest generation of neural networks has made major performance advances in object categorization from raw images. In particular, deep convolutional neural networks currently outperform alternative approaches on standard benchmarks by wide margins and achieve human-like accuracy on some tasks. These engineering successes present an opportunity to explore long-standing questions about the nature of human concepts by putting psychological theories to test at an unprecedented scale. This paper evaluates deep convolutional networks trained for classification on their ability to predict category typicality - a variable of paramount importance in the psychology of concepts - from the raw pixels of naturalistic images of objects. We find that these models have substantial predictive power, unlike simpler features computed from the same massive dataset, showing how typicality might emerge as a byproduct of a complex model trained to maximize classification performance.

Original languageEnglish (US)
Title of host publicationProceedings of the 37th Annual Meeting of the Cognitive Science Society, CogSci 2015
EditorsDavid C. Noelle, Rick Dale, Anne Warlaumont, Jeff Yoshimi, Teenie Matlock, Carolyn D. Jennings, Paul P. Maglio
PublisherThe Cognitive Science Society
Pages1243-1248
Number of pages6
ISBN (Electronic)9780991196722
StatePublished - 2015
Event37th Annual Meeting of the Cognitive Science Society: Mind, Technology, and Society, CogSci 2015 - Pasadena, United States
Duration: Jul 23 2015Jul 25 2015

Publication series

NameProceedings of the 37th Annual Meeting of the Cognitive Science Society, CogSci 2015

Conference

Conference37th Annual Meeting of the Cognitive Science Society: Mind, Technology, and Society, CogSci 2015
Country/TerritoryUnited States
CityPasadena
Period7/23/157/25/15

Keywords

  • categorization
  • deep learning
  • neural networks
  • object recognition
  • typicality

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Human-Computer Interaction
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Deep Neural Networks Predict Category Typicality Ratings for Images'. Together they form a unique fingerprint.

Cite this