Yc. Chu et K. Glover, Bounds of the induced norm and model reduction errors for systems with repeated scalar nonlinearities, IEEE AUTO C, 44(3), 1999, pp. 471-483
The class of nonlinear systems described by a discrete-time state equation
containing a repeated scalar nonlinearity as in recurrent neural networks i
s considered. Sufficient conditions are derived for the stability and induc
ed norm of such systems using positive definite diagonally dominant Lyapuno
v functions or storage functions, satisfying appropriate linear matrix ineq
ualities. Results are also presented for model reduction errors for such sy
stems.