Abstract
The idea of Artificial Neural Networks (ANN) is to build a massively connected and highly parallel system from simple processing units. This idea stems from real biological systems. These units are regarded as simplification of biological neurons what explains the ANN term. The information in ANN is stored in “weights” of connections between the units. It is assumed that ANN “adapts” to a problem by changing these weights.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Mockus, J., Eddy, W., Mockus, A., Mockus, L., Reklaitis, G. (1997). Optimization in Neural Networks. In: Bayesian Heuristic Approach to Discrete and Global Optimization. Nonconvex Optimization and Its Applications, vol 17. Springer, Boston, MA. https://doi.org/10.1007/978-1-4757-2627-5_10
Download citation
DOI: https://doi.org/10.1007/978-1-4757-2627-5_10
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4419-4767-3
Online ISBN: 978-1-4757-2627-5
eBook Packages: Springer Book Archive