Cycle-symmetric matrices and convergent neural networks

DOI10.1016/S0167-2789(00)00134-2zbMath0986.92004MaRDI QIDQ5940290

Chih-Wen Shih, Chih-Wen Weng

Publication date: 4 June 2002

Published in: Physica D (Search for Journal in Brave)

zbMATH Keywords

Lyapunov function; convergence of dynamics; cycle-symmetric matrix

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

37N25: Dynamical systems in biology

92B20: Neural networks for/in biological studies, artificial life and related topics

34C37: Homoclinic and heteroclinic solutions to ordinary differential equations

Related Items

ON THE TEMPLATES CORRESPONDING TO CYCLE-SYMMETRIC CONNECTIVITY IN CELLULAR NEURAL NETWORKS, Transversal homoclinic orbits in a transiently chaotic neural network, Global consensus for discrete-time competitive systems, Global attraction and stability for Cohen--Grossberg neural networks with delays, New exponential stability results for delayed neural networks with time varying delays, Robust exponential stability of uncertain fuzzy Cohen-Grossberg neural networks with time-varying delays

Cites Work

• The symmetrization of matrices by diagonal matrices
• Competition, decision, and consensus
• Combinatorially symmetric matrices
• A class of convergent neural network dynamics
• Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
• Cellular neural networks: theory
• Neurons with graded response have collective computational properties like those of two-state neurons.
• COMPLETE STABILITY FOR STANDARD CELLULAR NEURAL NETWORKS
• Unnamed Item
• Unnamed Item
• Unnamed Item