You are not logged in.
Openly accessible

Scaling connectionist compositional representations

Flackert, John C., Tait, John and Littlefair, Guy 2004, Scaling connectionist compositional representations, in Compositional Connectionism in Cognitive Science : 2004 AAAI Fall Symposium, AAAI Press, Menlo Park, Calif., pp. 20-24.

Attached Files
Name Description MIMEType Size Downloads
littlefair-scalingconnectionist-2004.pdf Published version application/pdf 319.98KB 31

Title Scaling connectionist compositional representations
Author(s) Flackert, John C.
Tait, John
Littlefair, Guy
Conference name AAAI Fall Symposium (2004 : Arlington, Va.)
Conference location Arlington, Va.
Conference dates 21-24 Oct. 2004
Title of proceedings Compositional Connectionism in Cognitive Science : 2004 AAAI Fall Symposium
Editor(s) [Unknown]
Publication date 2004
Conference series AAAI Fall Symposium
Start page 20
End page 24
Total pages 5
Publisher AAAI Press
Place of publication Menlo Park, Calif.
Keyword(s) associative storage
data reduction
data storage equipment
information science
Summary The Recursive Auto-Associative Memory (RAAM) has come to dominate connectionist investigations into representing compositional structure. Although an adequate model when dealing with limited data, the capacity of RAAM to scale-up to real-world tasks has been frequently questioned. RAAM networks are difficult to train (due to the moving target effect) and as such training times can be lengthy. Investigations into RAAM have produced many variants in an attempt to overcome such limitations. We outline how one such model ((S)RAAM) is able to quickly produce context-sensitive representations that may be used to aid a deterministic parsing process. By substituting a symbolic stack in an existing hybrid parser, we show that (S)RAAM is more than capable of encoding the real-world data sets employed. We conclude by suggesting that models such as (S)RAAM offer valuable insights into the features of connectionist compositional representations.
Language eng
Field of Research 099999 Engineering not elsewhere classified
Socio Economic Objective 970109 Expanding Knowledge in Engineering
HERDC Research category E2.1 Full written paper - non-refereed / Abstract reviewed
Copyright notice ©2004, American Association for Artificial Intelligence
Persistent URL http://hdl.handle.net/10536/DRO/DU:30038892

Document type: Conference Paper
Collections: School of Engineering
Open Access Collection
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 1 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 38 Abstract Views, 31 File Downloads  -  Detailed Statistics
Created: Thu, 20 Oct 2011, 12:39:35 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.