Delay-independent exponential stability of recurrent neural networks

作者：Zhao HY^*; Wang GL

来源：Physics Letters A, 2004, 333(5-6): 399-407.

DOI：10.1016/j.physleta.2004.10.040

• global exponential stability
• Lyapunov functional
• recurrent neural networks homeomorphism theory
• equilibrium point

In this Letter, the authors investigate further the recurrent neural networks model with delays. and give some sufficient criteria ensuring existence, uniqueness and global exponential stability (GES) of the equilibrium point by employing the inequality a Pi(k)(m) = 1 b(k)(ak) less than or equal to (1)/(r) Sigma(k)(m) = 1 q(k)b(k)(r) + (1)/(r) a(r) ( a greater than or equal to 0, b(k) greater than or equal to 0, q(k) > 0 with Sigma(k)(m) = 1 q(k) = r -1, and r > 1) constructing a new Lyapunov functional, and applying the homeomorphism theory. These criteria do not require the signal functions are differentiable. bounded and monotone nondecreasing. Thus the criteria obtained have highly important significance in solving optimization problems and reducing the neural computing time. Furthermore, we extend or improve the previously known results.

• 出版日期2004-12-13
• 单位南京大学; 新疆师范大学