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

reportActive / Technical Report | Accesssion Number: AD1186673 | DOI: 10.3233/978-1-60750-959-2-50 | Open PDF

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.

Author(s):
Chelian, Suhas E. ; Bhattacharyya, Rajan ; O'reilly, Randall
Author Organization(s):
HRL Laboratories, LLC; University of Colorado, Boulder
Funding Organization(s):
OFFICE OF THE DIRECTOR OF NATIONAL INTELLIGENCE WASHINGTON DC, WASHINGTON , DC
Document Type:
Technical Report/Book Chapter
Publication Date:
2011 Nov 01
Pagination:
6

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution Code:
A - Approved For Public Release
Distribution Statement: Public Release

RECORD

Collection: TRECMS
Subject Terms
Modernization Areas:
AI and Machine Learning
Communities of Interest:
Air Platforms
Descriptor(s):
neural networks, brain, information systems, recognition, information processing, neurosciences, computer programming, invariance, learning, sequences, symbols, training, computer vision, language, maintenance, materials, neuroimaging
Keyword(s):
IARPA Collection, prefrontal cortex (PFC), working memory, categorization, scene recognition
Creation Date:
2022 Dec 02
Update Date:
2022 Dec 02