Title :
On decision-boundary-based approaches for structure selection of multilayered neural nets
Author :
Chen, D. ; Burrell, P.
Author_Institution :
Sch. of Comput., Inf. Syst. & Math., South Bank Univ., London, UK
Abstract :
The optimal structure design for the multilayer feedforward neural network (MFNN) based classifier is of a fundamental importance in the neural network research area. In this paper several typical decision-boundary-based methods for the optimal structure design of the MFNN-based classifier are discussed. The main characteristics of each approach are analyzed and compared. Finally, future research directions are outlined
Keywords :
multilayer perceptrons; optimisation; pattern recognition; MFNN; decision-boundary-based approaches; decision-boundary-based methods; multilayer feedforward neural network structure; optimal structure design; structure selection; Computer networks; Feature extraction; Feedforward neural networks; Information systems; Mathematics; Multi-layer neural network; Neural networks; Pattern classification; Pattern matching; Pattern recognition;
Conference_Titel :
Info-tech and Info-net, 2001. Proceedings. ICII 2001 - Beijing. 2001 International Conferences on
Conference_Location :
Beijing
Print_ISBN :
0-7803-7010-4
DOI :
10.1109/ICII.2001.983104
