Title :
On a class of globally stable neural circuits
Author :
Kaszkurewicz, Eugenius ; Bhaya, Amit
Author_Institution :
Dept. of Electr. Eng., Federal Univ. of Rio de Janeiro, Brazil
fDate :
2/1/1994 12:00:00 AM
Abstract :
The authors show that diagonal stability of the interconnection matrix leads to a simple proof of the existence, uniqueness, and global asymptotic stability of the equilibrium of a Hopfield-Tank neural circuit, without making some common restrictive assumptions used in earlier results. It is also shown that the same condition guarantees structural stability, which ensures the desirable property of persistence of global asymptotic stability under general C1 perturbations
Keywords :
Hopfield neural nets; circuit theory; matrix algebra; stability criteria; Hopfield-Tank neural circuit; diagonal stability; equilibrium; general C1 perturbations; global asymptotic stability; globally stable neural circuits; interconnection matrix; structural stability; Analog circuits; Associative memory; Asymptotic stability; Circuit stability; Equations; Hardware; Integrated circuit interconnections; Neural networks; Quantization; Robust stability;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
