✦ LIBER ✦

Absolute stability of neural networks

✍ Scribed by Kiyotoshi Matsuoka

Publisher: John Wiley and Sons
Year: 1992
Tongue: English
Weight: 541 KB
Volume: 23
Category: Article
ISSN: 0882-1666
DOI: 10.1002/scj.4690230309

No coin nor oath required. For personal study only.

✦ Synopsis

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 stability conditions have been proposed for asymmetric recurrent networks, they are too strict and not useful for actual neural networks. Six new stability conditions are derived herein by using two types of Lyapunov functions. Some of them provide milder constraints on the connection weights than the conventional results, and others are particularly useful when the mutual connections between units have opposite signs of weights.

📜 SIMILAR VOLUMES

New necessary and sufficient conditions

New necessary and sufficient conditions for absolute stability of neural networks

✍ Tianguang Chu; Cishen Zhang 📂 Article 📅 2007 🏛 Elsevier Science 🌐 English ⚖ 341 KB

This paper presents new necessary and sufficient conditions for absolute stability of asymmetric neural networks. The main result is based on a solvable Lie algebra condition, which generalizes existing results for symmetric and normal neural networks. An exponential convergence estimate of the neur

Absolute stability of a class of neural

Absolute stability of a class of neural networks with unbounded delay

✍ Jiye Zhang 📂 Article 📅 2004 🏛 John Wiley and Sons 🌐 English ⚖ 115 KB 👁 1 views

Absolutely exponential stability of a cl

Absolutely exponential stability of a class of neural networks with unbounded delay

✍ Jiye Zhang; Yoshihiro Suda; Takashi Iwasa 📂 Article 📅 2004 🏛 Elsevier Science 🌐 English ⚖ 146 KB

Comments on “Absolute exponential stabil

Comments on “Absolute exponential stability of a class of neural networks with unbounded delay”

✍ Da-Wei Chang 📂 Article 📅 2007 🏛 Elsevier Science 🌐 English ⚖ 137 KB

Recently, Zhang, Suda and Iwasa [Zhang, Jiye, Suda, Yoshihiro, & Iwasa, Takashi (2004). Absolute exponential stability of a class of neural networks with unbounded delay, Neural Network, 17, 391-397] established the following: Result. Suppose that T be an n × n matrix, and D be an n × n positive de

Absolute exponential stability of recurr

Absolute exponential stability of recurrent neural networks with Lipschitz-continuous activation functions and time delays

✍ Jinde Cao; Jun Wang 📂 Article 📅 2004 🏛 Elsevier Science 🌐 English ⚖ 225 KB

A comment on ‘Absolute stability of a cl

A comment on ‘Absolute stability of a class of neural networks with unbounded delay’ by J. Zhang

✍ Jiye Zhang 📂 Article 📅 2004 🏛 John Wiley and Sons 🌐 English ⚖ 47 KB