Creating hierarchical categories using cell assemblies
Article
Huyck, C. 2007. Creating hierarchical categories using cell assemblies. Connection Science. 19 (1), pp. 1-24. https://doi.org/10.1080/09540090600779713
Type | Article |
---|---|
Title | Creating hierarchical categories using cell assemblies |
Authors | Huyck, C. |
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. |
Keywords | cell assembly; attractor net; Hebbian learning; hierarchical categorization |
Research Group | Artificial Intelligence group |
Publisher | Taylor and Francis |
Journal | Connection Science |
ISSN | 0954-0091 |
Electronic | 1360-0494 |
Publication dates | |
Online | 16 Mar 2007 |
Mar 2007 | |
Publication process dates | |
Deposited | 17 Oct 2008 |
Submitted | 08 Mar 2006 |
Output status | Published |
Digital Object Identifier (DOI) | https://doi.org/10.1080/09540090600779713 |
Web of Science identifier | WOS:000245629300001 |
Language | English |
Permalink -
https://repository.mdx.ac.uk/item/80v44
56
total views0
total downloads1
views this month0
downloads this month