Title :
An adaptive approach for optimal data reduction using recursive least squares learning method
Author :
Bannour, S. ; Azimi-Sadjadi, M.R.
Author_Institution :
Dept. of Electr. Eng., Colorado State Univ., Fort Collins, CO, USA
Abstract :
An approach is introduced for the recursive computation of the principal components of a vector stochastic process. The neurons of a single-layer perceptron are sequentially trained using a recursive least squares (RLS)-type algorithm to extract the principal components of the input process. The proof of the convergence of the weights at the n th neuron to the nth principal component, given that the previous (n-1) training steps have determined the first (n -1) principal components, is established. Simulation results are given to show the accuracy and speed of this algorithm in comparison with previous methods
Keywords :
convergence; learning (artificial intelligence); least squares approximations; neural nets; stochastic processes; adaptive approach; convergence; optimal data reduction; recursive least squares learning method; single-layer perceptron; vector stochastic process; Convergence; Eigenvalues and eigenfunctions; Learning systems; Least squares methods; Neural networks; Neurons; Principal component analysis; Resonance light scattering; Stochastic processes; Vectors;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0532-9
DOI :
10.1109/ICASSP.1992.226061
