Title :
A rigorous analysis of Linsker´s Hebbian learning network
Author :
Feng, Jianfeng ; Pan, Hong ; Roychowdhury, Vwani P.
Author_Institution :
Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
fDate :
27 Jun-1 Jul 1994
Abstract :
We propose a novel approach for a rigorous analysis of the nonlinear asymmetric dynamics of Linsker´s (1986) unsupervised Hebbian learning network. The results provide for the first time comprehensive explanations of the origin of the various structured connection patterns and of the roles of the different system parameters of the model. Our theoretical predictions are corroborated by numerical simulations
Keywords :
Hebbian learning; feedforward neural nets; multilayer perceptrons; multilayered unsupervised network; nonlinear asymmetric dynamics; numerical simulations; self-organization mechanism; structured connection patterns; system parameters; unsupervised Hebbian learning network; Covariance matrix; Density functional theory; Ear; Equations; Hebbian theory; Intelligent networks; Nonlinear dynamical systems; Numerical simulation; Shape; Visual system;
Conference_Titel :
Information Theory, 1994. Proceedings., 1994 IEEE International Symposium on
Conference_Location :
Trondheim
Print_ISBN :
0-7803-2015-8
DOI :
10.1109/ISIT.1994.394749
