๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Compactness of a set of multilayer neural networks and existence of neural network optimal control

โœ Scribed by Hiroshi Yamazaki; Yasunari Shidama; Masayoshi Eguchi; Hiromi Kobayashi


Publisher
John Wiley and Sons
Year
1997
Tongue
English
Weight
800 KB
Volume
80
Category
Article
ISSN
1042-0967

No coin nor oath required. For personal study only.


๐Ÿ“œ SIMILAR VOLUMES


An optimal control model of neural netwo
โœ Qiang Song; Robert P. Leland ๐Ÿ“‚ Article ๐Ÿ“… 1998 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 67 KB ๐Ÿ‘ 2 views

Optimization neural networks have been studied and applied in the literature, and the mechanism of such neural networks has been investigated from the point of view of optimization theory. Yet, no studies have been found by the authors to investigate the mechanism from a control systems' perspective

Feedback control of minimum-time optimal
โœ C. J. Goh; N. J. Edwards; A. Y. Zomaya ๐Ÿ“‚ Article ๐Ÿ“… 1993 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 925 KB

This paper presents an optimal feedback controller capable of driving a non-linear control system from an arbitrary initial state to a fixed final state in minimum time. The controller is based on a feedforward multilayer neural network trained repeatedly using open-loop optimal control data which d

Optimizing the parameters of multilayere
โœ M. S. Packianather; P. R. Drake; H. Rowlands ๐Ÿ“‚ Article ๐Ÿ“… 2000 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 252 KB ๐Ÿ‘ 1 views

The size and training parameters of artificial neural networks have a critical effect on their performance. This paper presents the application of the Taguchi Design of Experiments (DoEs) off-line quality control method in the optimization of the design parameters of a neural network. Being a 'paral

A novel multicriteria optimization algor
โœ Krishna Kottathra; Yianni Attikiouzel ๐Ÿ“‚ Article ๐Ÿ“… 1996 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 195 KB

We propose in this paper a novel prescriptive solution to decide the optimum number of neurons in the hidden-layer of multilayer feedforward neural networks. Our approach uses the unconstrained mixed integer nonlinear multicriteria optimization technique. We validate the algorithm using numerical ex