Accession Number:

ADA218909

Title:

Four Capacity Models for Coarse-Coded Symbol Memories

Descriptive Note:

Technical rept.

Corporate Author:

CARNEGIE-MELLON UNIV PITTSBURGH PA ARTIFICIAL INTELLIGENCE AND PSYCHOLOGY PROJECT

Report Date:

1987-12-15

Pagination or Media Count:

19.0

Abstract:

Coarse-coded symbol memories have appeared in several neutral network symbol processing models. In order to determine how these models would scale, one must first have some understanding of the mathematics of coarse-coded representations. We define the general structure of coarse-coded symbol memories, and discuss their strengths and weaknesses. Memory schemes can be characterized by their memory size, symbol-set size and capacity. We derive mathematical relationships between these parameters for various memory schemes, using both analysis and numerical methods. Finally, we compare the predicted capacity of one of the schemes with actual measurements of the coarse-coded working memory of distributed connectionist production system DCPS, Touretzky and Hintons distributed connectionist production system. jg

Subject Categories:

  • Computer Programming and Software

Distribution Statement:

APPROVED FOR PUBLIC RELEASE