journal contribution
posted on 2008-01-01, 00:00 authored by Ronald Rosenfeld, David S Touretzky, Artificial Intelligence and Psychology Project. Abstract: "Coarse-coded symbol memories have appeared in several neural 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 DCPS, Touretzky and Hinton's distributed connectionist production system."
History
Publisher Statement
Author's Pre-print: author can archive pre-print (ie pre-refereeing)
Author's Post-print: author can archive post-print (ie final draft post-refereeing)
Publisher's Version/PDF: author cannot archive publisher's version/PDF
General Conditions:
On author's or employer's website or funders mandated repository only
On a non-profit server
Pre-prints can be deposited on public repositories as long as accompanied by ACM copyright notice upon transfer of copyright
Post-prints can only be deposited in public repositories with explicit permission of publisher
Cannot use publisher version
Publisher copyright and source must be acknowledged
Must link to publisher version with statement that this is the definitive version and DOI
Must state that version on repository is the authors version
Set statement "© ACM, YYYY. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in PUBLICATION, {VOL#, ISS#, (DATE)} http://doi.acm.org/10.1145/nnnnnn.nnnnnn"Date
2008-01-01