Please use this identifier to cite or link to this item:
https://doi.org/10.1016/0933-3657(95)00019-4
Title: | Extracting rules from pruned neural networks for breast cancer diagnosis | Authors: | Setiono, R. | Keywords: | Breast cancer diagnosis Neural network pruning Penalty function Rule extraction |
Issue Date: | Feb-1996 | Citation: | Setiono, R. (1996-02). Extracting rules from pruned neural networks for breast cancer diagnosis. Artificial Intelligence in Medicine 8 (1) : 37-51. ScholarBank@NUS Repository. https://doi.org/10.1016/0933-3657(95)00019-4 | Abstract: | A new algorithm for neural network pruning is presented. Using this algorithm, networks with small number of connections and high accuracy rates for breast cancer diagnosis are obtained. We will then describe how rules can be extracted from a pruned network by considering only a finite number of hidden unit activation values. The accuracy of the extracted rules is as high as the accuracy of the pruned network. For the breast cancer diagnosis problem, the concise rules extracted from the network achieve an accuracy rate of more than 95% on the training data set and on the test data set. | Source Title: | Artificial Intelligence in Medicine | URI: | http://scholarbank.nus.edu.sg/handle/10635/99281 | ISSN: | 09333657 | DOI: | 10.1016/0933-3657(95)00019-4 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.