Constrained Optimisation for Switching Using Neural Networks
Systems Research Division, BT LaboratoriesMartlesham Heath, Ipswich IP5 7RE, United Kingdomsamin@bt-sys.bt.co.uk
Abstract
A methodical approach to the determination of optimisation parameters which give good convergence in the Hopfield dynamical model for a switching problem is presented. It is shown how the introduction of an imposed attractor into the network enables the model to be computationally operational for all types of random input request matrix.
1 Introduction
A switch can be regarded as a device which takes a set of n input signals and reproduces them in an order required by the switching mechanism. A request for a call connection through that switch ...
Get Proceedings of the International Workshop on Applications of Neural Networks to Telecommunications now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
