Supervised learning process of multi-layer perceptron neural networks using fast least squares

Author

Azimi-Sadjadi, Mahmood R. ; Citrin, Stuart ; Sheedvash, Sassan

Author_Institution

Dept. of Electr. Eng., Colorado State Univ., Ft. Collins, CO, USA

fYear

1990

fDate

3-6 Apr 1990

Firstpage

1381

Abstract

A new approach for the learning process of multilayer perceptron neural networks using a recursive-least-squares-(RLS) type algorithm is proposed. The weights in the network are updated recursively upon the arrival of a new training sample. To determine the desired target in the hidden layers an analog of the back-propagation strategy used in the conventional learning algorithms is developed. This permits the application of the learning procedure to all the other lower layers. Simulation results on the 4-b parity checker problem are provided

Keywords

learning systems; least squares approximations; neural nets; 4-bit parity checker problem; RLS algorithm; multilayer perceptron neural networks; recursive least squares algorithm; simulation results; supervised learning process; Computational modeling; Computer networks; Convergence; Least squares approximation; Least squares methods; Multi-layer neural network; Multilayer perceptrons; Neural networks; Resonance light scattering; Supervised learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115644

Filename

115644