Please use this identifier to cite or link to this item: http://hdl.handle.net/1783.1/1834

Constructive neural networks : some practical considerations

Authors KWOK, T.Y.
YEUNG, DY
Issue Date 1994
Source 1994 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOL 1-7 , 1994, p. 198-203
Summary 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.
Subjects
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.
Language English
Format Conference paper
Access View full-text via Web of Science
Files in this item:
File Description Size Format
icnn94.pdf 188123 B Adobe PDF