Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Help & Advice
University of Warwick

The Library

  • Login
  • Admin

The effects of varying memory vector size in a network that learns to learn

Tools
- Tools
+ Tools

Brown, G. D. A. (Gordon D. A.), Hyland, P. and Hulme, Charles (1994) The effects of varying memory vector size in a network that learns to learn. In: IEEE World Congress on Computational Intelligence, Orlando, USA, 27 Jun - 2 Jul 1994. Published in: Proceedings of the 1994 IEEE International Conference on Neural Networks : IEEE World Congress on Computational Intelligence, Vol.4 pp. 2291-2296. ISSN 9780780319028 . doi:10.1109/ICNN.1994.374576

Research output not available from this repository, contact author.
Official URL: http://dx.doi.org/10.1109/ICNN.1994.374576

Request Changes to record.

Abstract

Simulation results show that DARNET, a network model that learns using a gradient-descent procedure to perform single-trial learning, can make efficient use of whatever number of memory trace vector elements it is provided with. However, the effective maximum capacity of the system is determined by the architecture of the model to be the number of items that can be stored in a composite memory trace vector of fixed dimensionality, the optimal size depending on the number of elements in each to-be-associated input vector. DARNET has previously been shown to provide a good account of some relevant psychological data and the present work adds to the authors' understanding of the constraints governing its memory capacity and ability to "learn-to-learn"

Item Type: Conference Item (Paper)
Subjects: B Philosophy. Psychology. Religion > BF Psychology
Q Science > QA Mathematics
Divisions: Faculty of Science > Psychology
Library of Congress Subject Headings (LCSH): Memory -- Mathematical models, Convolutions (Mathematics), Neural networks (Computer science), Learning -- Mathematical models
Journal or Publication Title: Proceedings of the 1994 IEEE International Conference on Neural Networks : IEEE World Congress on Computational Intelligence
Publisher: IEEE Neural Networks Council
ISSN: 9780780319028
Book Title: Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94)
Official Date: 1994
Dates:
DateEvent
1994Published
Volume: Vol.4
Page Range: pp. 2291-2296
DOI: 10.1109/ICNN.1994.374576
Status: Peer Reviewed
Publication Status: Published
Conference Paper Type: Paper
Title of Event: IEEE World Congress on Computational Intelligence
Type of Event: Conference
Location of Event: Orlando, USA
Date(s) of Event: 27 Jun - 2 Jul 1994

Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item
twitter

Email us: wrap@warwick.ac.uk
Contact Details
About Us