Title :
Matrix tests for period 1 and 2 limit cycles in discrete threshold networks
Author_Institution :
Dept. of Electr. Eng., Southern Illinois Univ., Carbondale, IL, USA
Abstract :
The dynamics of discrete threshold neural networks is studied using a matrix inequality which is shown to be equivalent to the nonlinear state transition equation of the network. Some matrix tests for the existence of period 1 and 2 limit cycles are presented. Some types of vector sequences are shown not to be limit cycles
Keywords :
limit cycles; neural nets; discrete threshold neural networks; matrix inequality; matrix tests; nonlinear state transition equation; period 1 limit cycles; period 2 limit cycles; vector sequences; Associative memory; Convergence; Intelligent networks; Limit-cycles; Linear matrix inequalities; Neurons; Nonlinear equations; Pattern recognition; Symmetric matrices; Testing;
Journal_Title :
Systems, Man and Cybernetics, IEEE Transactions on
