HKUST Library Institutional Repository Banner

HKUST Institutional Repository >
Computer Science and Engineering >
CSE Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1783.1/1834
Title: Constructive neural networks : some practical considerations
Authors: Kwok, Tin-Yau
Yeung, Dit-Yan
Keywords: Constructive Neural networks
Objective function
Hidden unit functions
Chaotic time series
Hilbert space
Issue Date: 1994
Citation: Proceedings of the IEEE International Conference on Neural Networks, Orlando, FL, USA, 27 June-2 July 1994, IEEE Neural Networks Council, Piscataway, N. J., USA, 1994, p. 198-203
Abstract: Based on a Hilbert space point of view, we proposed in our previous work a novel objective function for training new hidden units in a constructive feedforward neural network. Moreover, we proved that if the hidden unit functions satisfy the universal approximation property, the network so constructed incrementally, using the proposed objective function and with input weight freezing, still preserves the universal approximation property with respect to L2 performance criteria. In this paper, we provide experimental support for the feasibility of using this objective function. Experiments are performed on two chaotic time series with encouraging results. In passing, we also demonstrate that engineering problems are not to be neglected in practical implementations. We identify the problem of plateau, and then show that by suitably transforming the objective function and modifying the quickprop algorithm, significant improvement can be obtained.
Rights: © 1994 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
URI: http://hdl.handle.net/1783.1/1834
Appears in Collections:CSE Conference Papers

Files in This Item:

File Description SizeFormat
icnn94.pdfpre-published version183KbAdobe PDFView/Open

All items in this Repository are protected by copyright, with all rights reserved.