File(s) not publicly available
Global optimisation of neural networks using a deterministic hybrid approach
conference contribution
posted on 2001-01-01, 00:00 authored by Gleb BeliakovGleb Beliakov, A AbrahamSelection 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.
History
Title of proceedings
Hybrid information systemsEvent
International Workshop on Hybrid Intelligent Systems (2001 : Adelaide, S. Aust.)Pagination
79 - 92Publisher
Physica-VerlagLocation
AdelaidePlace of publication
Heidelburg, GermanyStart date
2001-12-11End date
2001-12-12ISBN-13
9783790814804ISBN-10
3790814806Language
engPublication classification
E1 Full written paper - refereedEditor/Contributor(s)
A AbrahamUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC