Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/54243
Title: | A hierarchical incremental learning approach to task decomposition | Authors: | Guan, S.-U. Li, P. |
Keywords: | Incremental learning Neural network Ordering Task decomposition |
Issue Date: | 2002 | Citation: | Guan, S.-U.,Li, P. (2002). A hierarchical incremental learning approach to task decomposition. Journal of Intelligent Systems 12 (3) : 201-223. ScholarBank@NUS Repository. | Abstract: | In this paper, we propose a new task decomposition approach- hierarchical incremental class learning (HICL). In this approach, a K -class problem is divided into K sub-problems. The sub-problems are learnt sequentially in a hierarchical structure with K sub-networks. Each sub-network takes the output from the sub-network immediately below it as well as the original input as its input. The output from each sub-network contains one more class than the sub-network immediately below it, and this output is fed into the sub-network above it. It not only reduces harmful interference among hidden layers, but also facilitates information transfer between classes during training. The later sub-networks can obtain learnt information from the earlier sub-networks. We also proposed two ordering algorithms - Minimal-Side-Effect-First ordering method based on Class Decomposition Error (MSEF-CDE) and Minimal Side-Effect Ordering based on Fisher's Linear Discriminant (MSEF-FLD) to determine the hierarchical relationship between the sub-networks. The proposed HICL approach shows smaller regression error and classification error than classical decomposition approaches. | Source Title: | Journal of Intelligent Systems | URI: | http://scholarbank.nus.edu.sg/handle/10635/54243 | ISSN: | 03341860 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.