Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/112640
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | A neurobiologically plausible vector symbolic architecture |
Author: | Padilla, D. McDonnell, M. |
Citation: | Proceedings of the 8th IEEE International Conference on Semantic Computing (ICSC 2014), 2014, pp.242-245 |
Publisher: | IEEE |
Publisher Place: | online |
Issue Date: | 2014 |
Series/Report no.: | IEEE International Conference on Semantic Computing |
ISBN: | 147994002X 9781479940028 |
ISSN: | 2325-6516 |
Conference Name: | 8th IEEE International Conference on Semantic Computing (ICSC 2014) (16 Jun 2014 - 18 Jun 2014 : California) |
Statement of Responsibility: | Daniel E. Padilla and Mark D. McDonnell |
Abstract: | Vector Symbolic Architectures (VSA) are approaches to representing symbols and structured combinations of symbols as high-dimensional vectors. They have applications in machine learning and for understanding information processing in neurobiology. VSAs are typically described in an abstract mathematical form in terms of vectors and operations on vectors. In this work, we show that a machine learning approach known as hierarchical temporal memory, which is based on the anatomy and function of mammalian neocortex, is inherently capable of supporting important VSA functionality. This follows because the approach learns sequences of semantics-preserving sparse distributed representations. |
Rights: | © 2014 IEEE |
DOI: | 10.1109/ICSC.2014.40 |
Grant ID: | http://purl.org/au-research/grants/arc/DP1093425 |
Published version: | https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6881542 |
Appears in Collections: | Aurora harvest 3 Electrical and Electronic Engineering publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.