Title :
A novel learning law for a single neuron
Author :
Shin, Seiichi ; Shiozawa, Yoichi
Author_Institution :
Dept. of Math. Eng. & Inf. Phys., Tokyo Univ., Japan
Abstract :
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 σ-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
Keywords :
adaptive systems; learning (artificial intelligence); neural nets; parameter estimation; adaptive control systems; adaptive law; boundedness; learning gain; learning law; neural nets; neuron; robust control; Adaptive control; Convergence; Facsimile; Information science; Neural networks; Neurons; Numerical simulation; Physics; Programmable control; Robust control;
Conference_Titel :
Industrial Electronics, Control, and Instrumentation, 1993. Proceedings of the IECON '93., International Conference on
Conference_Location :
Maui, HI
Print_ISBN :
0-7803-0891-3
DOI :
10.1109/IECON.1993.339064
