Global optimisation of neural networks using a deterministic hybrid approach

Beliakov, Gleb and Abraham, Ajith 2001, Global optimisation of neural networks using a deterministic hybrid approach, in Hybrid information systems, Physica-Verlag, Heidelburg, Germany, pp. 79-92.

Attached Files
Name Description MIMEType Size Downloads

Title Global optimisation of neural networks using a deterministic hybrid approach
Author(s) Beliakov, GlebORCID iD for Beliakov, Gleb
Abraham, Ajith
Conference name International Workshop on Hybrid Intelligent Systems (2001 : Adelaide, S. Aust.)
Conference location Adelaide
Conference dates 11-12 December 2001
Title of proceedings Hybrid information systems
Editor(s) Abraham, Ajith
Publication date 2001
Start page 79
End page 92
Publisher Physica-Verlag
Place of publication Heidelburg, Germany
Summary Selection of the topology of a neural network and correct parameters for the learning algorithm is a tedious task for designing an optimal artificial neural network, which is smaller, faster and with a better generalization performance. In this paper we introduce a recently developed cutting angle method (a deterministic technique) for global optimization of connection weights. Neural networks are initially trained using the cutting angle method and later the learning is fine-tuned (meta-learning) using conventional gradient descent or other optimization techniques. Experiments were carried out on three time series benchmarks and a comparison was done using evolutionary neural networks. Our preliminary experimentation results show that the proposed deterministic approach could provide near optimal results much faster than the evolutionary approach.
ISBN 3790814806
Language eng
Field of Research 080108 Neural, Evolutionary and Fuzzy Computation
HERDC Research category E1 Full written paper - refereed
HERDC collection year 2002
Persistent URL

Connect to link resolver
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 3 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 916 Abstract Views, 0 File Downloads  -  Detailed Statistics
Created: Mon, 07 Jul 2008, 09:43:11 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact