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