Title :
Fast learning neural networks using transform domain LMS structure
Author :
Khurram, Muzaffar U. ; Ahmed, Hassan M. ; Rauf, Fawad
Author_Institution :
Nonlinear Modelling Lab., Boston Univ., MA, USA
Abstract :
Transform domain adaptive filtering, which uses orthogonal transforms to partially uncorrelate the colored input, thus reducing the eigenvalue spread, is extended to the nonlinear domain and used as the basis of a learning algorithm for neural networks. Computer simulations show that this neural structure learns much faster than least-mean-square-based structure
Keywords :
adaptive filters; learning (artificial intelligence); least squares approximations; neural nets; adaptive filtering; colored input; eigenvalue spread; learning algorithm; nonlinear domain; orthogonal transforms; transform domain LMS structure; Adaptive filters; Biological neural networks; Computer errors; Convergence; Eigenvalues and eigenfunctions; Equations; Filtering; Least squares approximation; Neural networks; Resonance light scattering;
Conference_Titel :
Circuits and Systems, 1992. ISCAS '92. Proceedings., 1992 IEEE International Symposium on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-0593-0
DOI :
10.1109/ISCAS.1992.230016
