Title :
Improved sufficient convergence condition for the discrete-time cellular neural networks
Author :
Park, Sungjun ; Chae, Soo-Ik
Author_Institution :
Video Res. Center, Daewoo Electron. Co., Seoul, South Korea
Abstract :
In this paper, we derive an improved sufficient convergence condition for discrete-time cellular neural networks (DTCNN) using the positive semidefinite (PSD) constraint and the boundary condition of DTCNN. The experimental results confirm that the derived condition offers a wider convergence range than the convergence condition of Fruehauf (1992). The new condition does not depend on the type of the nonlinear output function of the DTCNN
Keywords :
cellular neural nets; convergence; DTCNN; PSD constraint; convergence condition; discrete-time cellular neural networks; nonlinear output function; positive semidefinite constraint; Boundary conditions; Cellular neural networks; Convergence; Eigenvalues and eigenfunctions; Feedback; Hardware; Image processing; Piecewise linear techniques; Recurrent neural networks; Symmetric matrices;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.616195
