Showing papers by "József Bíró published in 1996"

Neural Networks for Exact Constrained Optimization

Abstract: The paper is concerned with analog neural networks which can solve nonlinear constrained optimization tasks using the penalty function approach. The neural model developed can be regarded as asymptotically exact dynamic solver in a sense that the equilibrium state represents a solution which can be arbitrarily close to that of the original constrained optimization task. Although it is a quite natural requirement, generally it can be fulfilled only with arbitrarily large penalty multipliers. The neural network presented overcomes this problem with the use of special nonlinearities, that is it can produce solutions arbitrarily close to the exact one at finite penalty multipliers. Stability analyses validating the usefulness of the model are also outlined.

Neural networks for logical partitioning of ATM networks

Abstract: One of the most important tasks in ATM networks is to satisfy the requirements of different services. An efficient way of providing the quality of service is the logical separation of network resources. It means that on top of the physical network a number of logical (virtual) subnetworks are established in which the logical links share the capacities of physical links. There are several advantages of logical resource separation, such as the network can operate more safely, the management can be simplified and some important structures, e.g. virtual leased networks, are much easier to implement. In this paper we describe how neural networks can be used in the algorithms that optimize the logical configuration. The validity and usefulness of the methods are shown by computer simulation. The most important practical implication is that the proposed neural structures can operate very fast in a parallel implementation, thus providing the network manager with the opportunity of running realtime applications of complex reconfiguration algorithms to enhance network flexibility via accelerated network intelligence.