Title :
Hebbian learning and self-association in nonlinear neural networks
Author :
Palmieri, Francesco
Author_Institution :
Connecticut Univ., CT, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
A self-organizing feature map, based on a Hebbian paradigm, is proposed as a universal adaptive memory. The learning paradigm, can be applied to arbitrary network topologies containing the standard sigmoidal nonlinearities at their nodes. The system generalizes the linear principal components by mapping the input space into a set of orthogonal nonlinear projections. Only localized learning rules are necessary for the adaptation. The size of the system is related to the desired accuracy and to the density of the examples
Keywords :
Hebbian learning; self-organising feature maps; Hebbian learning; arbitrary network topologies; learning paradigm; linear principal components; localized learning rules; nonlinear neural networks; orthogonal nonlinear projections; self-association; self-organizing feature map; sigmoidal nonlinearities; universal adaptive memory; Adaptive filters; Adaptive signal processing; Artificial neural networks; Biological neural networks; Biomedical signal processing; Hebbian theory; Intelligent networks; Network topology; Neural networks; Signal analysis;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374365
