NN-learning with backpropagation and adaptive filter techniques

Author

Humpert, Benedikt

Author_Institution

Houston Univ., TX, USA

Volume

1

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

470

Abstract

Explains current attempts using Kalman filter techniques in order to develop fast learning algorithms for feedforward neural networks (NN). There are two main ingredients: Taylor-series linearization during the weight updating process and backpropagation of the output errors according to the backpropagation (BP-) algorithm. Pointing to several other filter-based algorithms, the author discusses in somewhat more detail the least-square-lattice (LSL) approach which uses QR-decomposition. The QR-LSL algorithm has several advantages which make it to a highly interesting candidate for an efficient NN-learning algorithm

Keywords

Kalman filters; adaptive filters; backpropagation; feedforward neural nets; series (mathematics); Kalman filter; QR-decomposition; Taylor-series linearization; adaptive filter; backpropagation; feedforward neural networks; filter-based algorithms; learning; least-square-lattice; output errors; weight updating process; Adaptive filters; Backpropagation; Equations; Linear approximation; Stability; Vectors;

fLanguage

English

Publisher

ieee

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

Type

conf

DOI

10.1109/ICNN.1994.374208

Filename

374208