Learning Categories with Invariances in a Neural Network Model of Prefrontal Cortex

Abstract

Prefrontal cortex (PFC) is implicated in a number of functions including working memory and categorization. Here the Prefrontal cortex Basal Ganglia Working Memory (PBWM) model (O'Reilly and Frank, 2006) is applied to learning categories with invariances. In particular, motivated by a problem in scene recognition, objects in different locations are sequentially presented to the network for categorization. The model learns to recognize these classes without explicit programming, thus modeling human categorization along with characteristics such as generalization to novel sequences and frequency dependent effects. Future extensions to the current work including applications to other domains and modeling functionally distinct segregations of PFC and neuromodulatory systems are also described.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2011
Accession Number
AD1186673

Entities

People

  • Rajan Bhattacharyya
  • Randall C. O'Reilly
  • Suhas E. Chelian

Organizations

  • University of Colorado Boulder

Tags

Communities of Interest

  • Air Platforms

DTIC Thesaurus Topics

  • Brain
  • Computer Programming
  • Computer Vision
  • Information Processing
  • Information Systems
  • Invariance
  • Language
  • Learning
  • Maintenance
  • Materials
  • Neural Networks
  • Neuroimaging
  • Neurology
  • Neurosciences
  • Psychology
  • Recognition
  • Sequences
  • Symbols
  • Training

Fields of Study

  • Biology
  • Psychology

Readers

  • Neural Network Machine Learning.
  • Neuroscience

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks