A cascading structure and training method for multilayer neural network
Article
Article Title | A cascading structure and training method for multilayer neural network |
---|---|
ERA Journal ID | 32099 |
Article Category | Article |
Authors | Li, Yan (Author) and Rad, A. B. (Author) |
Journal Title | International Journal of Neural Systems |
Journal Citation | 8 (5/6), pp. 509-515 |
Number of Pages | 7 |
Year | 1997 |
Place of Publication | Singapore |
ISSN | 0129-0657 |
1793-6462 | |
Digital Object Identifier (DOI) | https://doi.org/10.1142/S0129065797000495 |
Abstract | A new structure and training method for multilayer neural networks is presented. The proposed method is based on cascade training of subnetworks and optimizing weights layer by layer. The training procedure is completed in two steps. First, a subnetwork, m inputs and n outputs as the style of training samples, is trained using the training samples. Secondly the outputs of the subnetwork is taken as the inputs and the outputs of the training sample as the desired outputs, another subnetwork with n inputs and n outputs is trained. Finally the two trained subnetworks are connected and a trained multilayer neural networks is created. The numerical simulation results based on both linear least squares back-propagation (LSB) and traditional back-propagation (BP) algorithm have demonstrated the efficiency of the proposed method. |
Keywords | back-propagation algorithm; linear least squares back-propagation; neural networks |
ANZSRC Field of Research 2020 | 469999. Other information and computing sciences not elsewhere classified |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Hong Kong Polytechnic University, China |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q25w5/a-cascading-structure-and-training-method-for-multilayer-neural-network
Download files
1700
total views55
total downloads4
views this month0
downloads this month