Abstract
The networks we have studied up to now were all operating in a deterministic fashion. If the network was in a particular state, the next state was always the same. This seems the very model of a reliable system that every engineer wants. If the network is used for optimization however, e.g. to solve the Travelling Salesman Problem [99], a network operating deterministically will usually not find the best solution. When converging towards an equilibrium, it will get stuck into a local optimum.
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-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
De Wilde, P. (1997). Neural Networks and Markov Chains. In: Neural Network Models. Springer, London. https://doi.org/10.1007/978-1-84628-614-8_8
Download citation
DOI: https://doi.org/10.1007/978-1-84628-614-8_8
Publisher Name: Springer, London
Print ISBN: 978-3-540-76129-7
Online ISBN: 978-1-84628-614-8
eBook Packages: Springer Book Archive