UOBScholar Hub
UOB Libraries created the UOBScholar Hub, an Institutional Repository (IR) for archiving and collecting all the research output of the UOB community. It aims to improve the visibility, usage and impact of research conducted at UOB. Materials included are: academic journal articles, conference papers and presentations, books and book chapters, ongoing research papers, reports and patents.
Submit your Publication
Please use this identifier to cite or link to this item:
https://scholarhub.balamand.edu.lb/handle/uob/450| Title: | A comparative study of the category choice of the fuzzy ART with the L -1 norm | Authors: | Dagher, Issam | Affiliations: | Department of Computer Engineering | Keywords: | Fuzzy neural nets Category theory ART neural nets Learning (artificial intelligence) |
Issue Date: | 2003 | Publisher: | IEEE | Part of: | Proceedings of the International Joint Conference on Neural Networks, 2003 | Start page: | 1969 | End page: | 1974 | Conference: | International Joint Conference on Neural Networks (20-24 July 2003 : Portland, OR, USA) | Abstract: | In this paper, a comparative study of the category choice of the Fuzzy ART with the L-1 norm is presented. It is shown that the category choice can be replaced by a distance measure related to the L-1 norm. This distance measure will have the following advantages over the category choice of the Fuzzy ART network: 1) no need for augmenting the dimensions of the input patterns. The distance measure will operate directly on the input patterns without the need for doing complement coding; and 2) no need for normalizing the input patterns. The input patterns need not to be in the interval. |
URI: | https://scholarhub.balamand.edu.lb/handle/uob/450 | Ezproxy URL: | Link to full text | Type: | Conference Paper |
| Appears in Collections: | Department of Computer Engineering |
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.