Reduced training for hierarchical incremental class learning

Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICCIS.2006.252321

Title:	Reduced training for hierarchical incremental class learning
Authors:	Bao, C. Guan, S.-U.
Keywords:	Classifier systems HICL Hierarchical learning Reduced training set
Issue Date:	2006
Citation:	Bao, C.,Guan, S.-U. (2006). Reduced training for hierarchical incremental class learning. 2006 IEEE Conference on Cybernetics and Intelligent Systems : -. ScholarBank@NUS Repository. https://doi.org/10.1109/ICCIS.2006.252321
Abstract:	Hierarchical Incremental Class Learning (HICL), proposed by Guan and Li in 2002 [13], is a recently proposed task decomposition method that addresses the pattern classification problem. HICL is proven to be a good classifier but closer examination reveals areas for potential improvement. This paper presents an approach to improve the classification accuracy of HICL by applying the concept of Reduced Pattern Training (RPT). The procedure for RPT is described and compared with the original training procedure. RPT systematically reduces the size of the training data set based on the order of sub-networks built. The results from benchmark classification problems show much promise for the improved model. © 2006 IEEE.
Source Title:	2006 IEEE Conference on Cybernetics and Intelligent Systems
URI:	http://scholarbank.nus.edu.sg/handle/10635/71589
ISBN:	1424400236
DOI:	10.1109/ICCIS.2006.252321
Appears in Collections:	Staff Publications

There are no files associated with this item.

Check