A novel learning law for a single neuron

In this paper, the learning gain is reconsidered from the viewpoint of the adaptive control systems. We present a novel learning law for a single neuron, which is a kind of /spl sigma/-modified adaptive law used in the robust adaptive control systems. We presents a brief proof of boundedness of the estimator to be learned and a simple numerical simulation, where we show the viability of the proposed learning law.<<ETX>>

[1]  S. Shin,et al.  Neuro-adaptive control for general nonlinear discrete-time systems , 1991, Proceedings IECON '91: 1991 International Conference on Industrial Electronics, Control and Instrumentation.

[2]  Yasuharu Shimeki,et al.  A State Traversal Algorithm Using a State Covariance Matrix , 1993, 30th ACM/IEEE Design Automation Conference.

[3]  Petar V. Kokotovic,et al.  Instability analysis and improvement of robustness of adaptive control , 1984, Autom..

[4]  S. Shin,et al.  Nonlinear state observer for sequential logic circuits , 1992, Proceedings of the 1992 International Conference on Industrial Electronics, Control, Instrumentation, and Automation.