Evaluating (and Improving) the Correspondence Between Deep Neural Networks and Human Representations

Joshua C. Peterson, Joshua T. Abbott, Thomas L. Griffiths

Research output: Contribution to journalArticlepeer-review

100 Scopus citations

Abstract

Decades of psychological research have been aimed at modeling how people learn features and categories. The empirical validation of these theories is often based on artificial stimuli with simple representations. Recently, deep neural networks have reached or surpassed human accuracy on tasks such as identifying objects in natural images. These networks learn representations of real-world stimuli that can potentially be leveraged to capture psychological representations. We find that state-of-the-art object classification networks provide surprisingly accurate predictions of human similarity judgments for natural images, but they fail to capture some of the structure represented by people. We show that a simple transformation that corrects these discrepancies can be obtained through convex optimization. We use the resulting representations to predict the difficulty of learning novel categories of natural images. Our results extend the scope of psychological experiments and computational modeling by enabling tractable use of large natural stimulus sets.

Original languageEnglish (US)
Pages (from-to)2648-2669
Number of pages22
JournalCognitive science
Volume42
Issue number8
DOIs
StatePublished - Nov 2018
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Experimental and Cognitive Psychology
  • Artificial Intelligence
  • Cognitive Neuroscience

Keywords

  • Artificial intelligence
  • Categorization
  • Neural networks
  • Similarity

Fingerprint

Dive into the research topics of 'Evaluating (and Improving) the Correspondence Between Deep Neural Networks and Human Representations'. Together they form a unique fingerprint.

Cite this