Title :
Convergence of a Hebbian-type learning algorithm
Author :
Zhang, Qingfu ; Leung, Yiu-Wing
Author_Institution :
Dept. of Comput. Sci., Changsha Inst. of Technol., Hunan, China
fDate :
12/1/1998 12:00:00 AM
Abstract :
A Hebbian-type learning algorithm was proposed by Gao et al. (1994) for extracting the minor components of the input signals. In this paper, we demonstrate that some solutions of the averaging differential equation of this algorithm can become unbounded in a finite time. We derive five sufficient conditions to ensure that the solutions of its averaging differential equation are bounded and can be extended to the time interval [0, ∞]. Any one of these conditions can guarantee that this algorithm can be used to find the minor components of the input signals
Keywords :
Hebbian learning; convergence; differential equations; Hebbian-type learning algorithm; averaging differential equation; bounded solutions; convergence; input signals; minor components; sufficient conditions; Approximation algorithms; Autocorrelation; Circuits; Convergence; Differential equations; H infinity control; Logic gates; Signal processing algorithms; Smart pixels; Vectors;
Journal_Title :
Circuits and Systems II: Analog and Digital Signal Processing, IEEE Transactions on
