Please use this identifier to cite or link to this item:
Title: A hierarchical incremental learning approach to task decomposition
Authors: Guan, S.-U. 
Li, P. 
Keywords: Incremental learning
Neural network
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
ISSN: 03341860
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

checked on Jun 28, 2019

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.