Title :
L-infinity analysis of Hopfield networks
Author :
Stoica, Adrian ; Yaesh, Isaac
Author_Institution :
Fac. of Aerosp. Eng., Univ. Politeh. of Bucharest, Bucharest, Romania
Abstract :
A non symmetric version of Hopfield networks subject to bounded disturbances is considered. Such networks arise in the context of visuo-motor control loops and may, therefore, be used to mimic their complex behavior. In this paper, we adopt the Lur´e-Postnikov systems approach to analyze the induced L∞8 gain of generalized Hopfield networks. The results are illustrated via a simple numerical example.
Keywords :
Hopfield neural nets; Hopfield networks; L-infinity analysis; Lure-Postnikov systems approach; visuo-motor control loops; Artificial neural networks; Ellipsoids; Noise; Stability analysis; Stochastic processes; Symmetric matrices; Trajectory; Hopfield networks; ellipsoids; nonlinear systems; robustness; stability;
Conference_Titel :
Computational Intelligence in Control and Automation (CICA), 2011 IEEE Symposium on
Conference_Location :
Paris
Print_ISBN :
978-1-4244-9902-1
DOI :
10.1109/CICA.2011.5945751
