Chen Tianping, Lu Wenlian, Amari Shun-ichi
Laboratory of Nonlinear Mathematics Science, Institute of Mathematics, Fudan University, Shanghai, China.
Neural Comput. 2002 Dec;14(12):2947-57. doi: 10.1162/089976602760805359.
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.