Please use this identifier to cite or link to this item:
Title: Dynamical optimal learning for FNN and its applications
Authors: Tang, H.J.
Tan, K.C. 
Lee, T.H. 
Issue Date: 2004
Citation: Tang, H.J.,Tan, K.C.,Lee, T.H. (2004). Dynamical optimal learning for FNN and its applications. IEEE International Conference on Fuzzy Systems 1 : 443-447. ScholarBank@NUS Repository.
Abstract: This paper presents a new dynamical optimal learning (DOL) algorithm for three-layer linear neural networks and investigates its generalization ability. The optimal learning rates can be fully determined during the training process. The mean squared error is guaranteed to be stably decreased and the learning is less sensitive to initial parameter settings. The simulation results illustrate that the proposed DOL algorithm gives better generalization performance and faster convergence as compared to standard error back propagation algorithm.
Source Title: IEEE International Conference on Fuzzy Systems
ISSN: 10987584
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 14, 2019

Google ScholarTM


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