Please use this identifier to cite or link to this item:
Title: Incremental self-growing neural networks with the changing environment
Authors: Su, L
Guan, SU
Yeo, YC
Keywords: Incremental learning;Cascade correlation networks;Self-growing neural networks;Incremental input;Changing environment
Issue Date: 2001
Publisher: Freund & Pettman
Citation: Journal of Intelligent Systems. 11 (1) 43 - 74
Abstract: Conventional incremental learning approaches in multi-layered feedforward neural networks are based on new incoming training instances. However, in this paper, changing environment is defined as new incoming features of a specific problem. Our empirical study illustrates that ISGNN, incremental self-growing neural networks, can adapt to such a changing environment with new input dimension. In the meanwhile, dynamic neural network algorithms are used for automatic network structure design in order to avoid time-consuming search for an appropriate network topology with the trial and error method. We also exploit information learned by the previous grown network so as to avoid retraining. Finally, we report simulation results on two benchmark problems. Our experiments show that this kind of adaptive learning mechanism could significantly improve the performance of original networks.
ISSN: 0334-1860
Appears in Collections:Electronic and Computer Engineering
Dept of Electronic and Computer Engineering Research Papers

Files in This Item:
File Description SizeFormat 
Closed Access - Guan et al - Journal of Intelligent Systems 2001.txt534 BTextView/Open

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