Title: | Two-level learning algorithm for multilayer neural networks |
Authors: | Liu, CS Tseng, CH 機械工程學系 Department of Mechanical Engineering |
Issue Date: | 1998 |
Abstract: | A two-level learning algorithm that decomposes multilayer neural networks into a set of sub-networks is presented. A lot of popular optimization methods, such as conjugate-gradient and quasi-Neurton methods, cart be utilized to train these sub-networks. In addition, if the activation functions are hard-limiting functions, the multilayer neural networks can be trained by the perceptron learning rule in this two-level learning algorithm. Two experimental problems are given as examples for this algorithm. |
URI: | http://hdl.handle.net/11536/19566 |
ISBN: | 0-7803-5214-9 |
ISSN: | 1082-3409 |
Journal: | TENTH IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, PROCEEDINGS |
Begin Page: | 97 |
End Page: | 102 |
Appears in Collections: | Conferences Paper |