๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

The stability and design of nonlinear neural networks

โœ Scribed by Xiangyang Gong; Wanyi Chen; Fengsheng Tu

Publisher
Elsevier Science
Year
1998
Tongue
English
Weight
363 KB
Volume
35
Category
Article
ISSN
0898-1221

No coin nor oath required. For personal study only.

โœฆ Synopsis

Based on the techniques of singular value decomposition and generalized inverse, two new methods for designing associative memories are presented. The two methods not only guarantee that each given vector is an equilibrium point of the network, but also guarantee the asymptotic stability of the equilibrium points. Examples show the effectiveness of the new methods.

๐Ÿ“œ SIMILAR VOLUMES

Absolute stability of neural networks
Absolute stability of neural networks
โœ Kiyotoshi Matsuoka ๐Ÿ“‚ Article ๐Ÿ“… 1992 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 541 KB

## Abstract A sufficient condition for the state of a recurrent neural network to converge stably to an equilibrium state is the symmetry of the weights of connections between constituent units. However, generally, it imposes a strong restriction on the capability of the network. Although several s