Creating hierarchical categories using cell assemblies

Huyck, Christian R. (2007) Creating hierarchical categories using cell assemblies. Connection Science, 19 (1). pp. 1-27. ISSN 0954-0091

Full text is not in this repository.

This item is available in: Library Catalogue

Abstract

This paper shows how the CA concept can be used to learn hierarchical categories. Elements of basic categories are presented to the system. It learns those categories, but also learns higher order categories. This system can use these categories for default reasoning. This is novel because it is all done with biologically plausible fatiguing Leaky Integrate and Fire neurons. It makes use of compensatory learning work to form CAs. This also shows neural support for the well worn psychological work in categorisation. This work is being used in a current EPSRC grant to provide semantic relatedness and reduce network size.

Item Type: Article
Research Areas: A. > School of Science and Technology > Computer Science
A. > School of Science and Technology > Computer Science > Artificial Intelligence group
ISI Impact: 8
Item ID: 73
Useful Links:
Depositing User: Repository team
Date Deposited: 17 Oct 2008 12:11
Last Modified: 13 Oct 2016 14:11
URI: http://eprints.mdx.ac.uk/id/eprint/73

Actions (login required)

Edit Item Edit Item