Related Experiment Videos
Global convergence rate of recurrently connected neural networks
Tianping Chen1, Wenlian Lu, Shun-ichi Amari
1Laboratory of Nonlinear Mathematics Science, Institute of Mathematics, Fudan University, Shanghai, China. tchen@fudan.edu.cn
Neural Computation
|December 19, 2002
Abstract:
We discuss recurrently connected neural networks, investigating their global exponential stability (GES). Some sufficient conditions for a class of recurrent neural networks belonging to GES are given. Sharp convergence rate is given too.