An alternative proof of convergence for Kung-Diamantaras APEX algorithm

Author

Chen, H. ; Liu, R.

Author_Institution

Dept. of Electr. Eng., Notre Dame Univ., IN, USA

fYear

1991

fDate

30 Sep-1 Oct 1991

Firstpage

40

Lastpage

49

Abstract

The problem of adaptive principal components extraction (APEX) has gained much interest. In 1990, a new neuro-computation algorithm for this purpose was proposed by S. Y. Kung and K. I. Diamautaras. (see ICASSP 90, p.861-4, vol.2, 1990). An alternative proof is presented to illustrate that the K-D algorithm is in fact richer than has been proved before. The proof shows that the neural network will converge and the principal components can be extracted, without assuming that some of projections of synaptic weight vectors have diminished to zero. In addition, the authors show that the K-D algorithm converges exponentially

Keywords

convergence; neural nets; signal processing; Kung-Diamantaras APEX algorithm; adaptive principal components extraction; convergence; neural network; neuro-computation algorithm; signal processing; synaptic weight vectors; Computer networks; Convergence; Covariance matrix; Eigenvalues and eigenfunctions; Joining processes; Neural networks; Principal component analysis; Signal processing; Signal processing algorithms; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing [1991]., Proceedings of the 1991 IEEE Workshop

Conference_Location

Princeton, NJ

Print_ISBN

0-7803-0118-8

Type

conf

DOI

10.1109/NNSP.1991.239537

Filename

239537