Searching for just a few words should be enough to get started. If you need to make more complex queries, use the tips below to guide you.
Article type: Research Article
Authors: Silva, Ricardo Bezerra de Andrade ea | Ludermir, Teresa Bernardab
Affiliations: [a] Center for Automated Learning and Discovery, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA, USA. E-mail: rbas@cs.cmu.edu | [b] Centro de Informática, Universidade Federal de Pernambuco, Av. Professor Luis Freire s/n, Cidade Universitária, 50740-540 Recife, PE, Brazil. E-mail: tbl@cin.ufpe.br
Abstract: Since there is no individual approach that can be universally applied to effectively solve the hard problems of artificial intelligence and data analysis, hybrid systems are necessary to better tackle specific tasks by exploiting the advantages of different methodologies in a single framework. Based on known results of combining neural networks and rule-based systems, this work presents a hybrid system with the purpose of simplifying rule sets obtained from rule induction algorithms on classification problems without increasing the accuracy error. This is motivated by assuming that simplicity can lead to more understandable models and rule induction algorithms often provide an excessive number of rules necessary to classify future examples within a given accuracy error, even after pruning. Experimental evidence suggests effective gains on a benchmark of sixteen data sets. Experiments were also performed to detect the effect of different components of the proposed approach in achieving the results and so helping to explain why this hybrid system works.
Keywords: hybrid systems, Occam's razor, classification
DOI: 10.3233/IDA-2001-5304
Journal: Intelligent Data Analysis, vol. 5, no. 3, pp. 227-244, 2001
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
USA
Tel: +1 703 830 6300
Fax: +1 703 830 2300
sales@iospress.com
For editorial issues, like the status of your submitted paper or proposals, write to editorial@iospress.nl
IOS Press
Nieuwe Hemweg 6B
1013 BG Amsterdam
The Netherlands
Tel: +31 20 688 3355
Fax: +31 20 687 0091
info@iospress.nl
For editorial issues, permissions, book requests, submissions and proceedings, contact the Amsterdam office info@iospress.nl
Inspirees International (China Office)
Ciyunsi Beili 207(CapitaLand), Bld 1, 7-901
100025, Beijing
China
Free service line: 400 661 8717
Fax: +86 10 8446 7947
china@iospress.cn
For editorial issues, like the status of your submitted paper or proposals, write to editorial@iospress.nl
如果您在出版方面需要帮助或有任何建, 件至: editorial@iospress.nl