Efficient training techniques for classification with vast input space

Author

Saad, E.W. ; Choi, J.J. ; Vian, J.L. ; Wunsch, D.C.

Author_Institution

Dept. of Electr. Eng., Texas Tech. Univ., Lubbock, TX, USA

Volume

2

fYear

1999

fDate

36342

Firstpage

1333

Abstract

Strategies to efficiently train a neural network for an aerospace problem with a large multidimensional input space are developed and demonstrated. The neural network provides classification for over 100,000,000 data points. A query-based strategy is used that initiates training using a small input set, and then augments the set in multiple stages to include important data around the network decision boundary. Neural network inversion and oracle query are used to generate the additional data, jitter is added to the query data to improve the results, and an extended Kalman filter algorithm is used for training. A causality index is discussed as a means to reduce the dimensionality of the problem based on the relative importance of the inputs

Keywords

Kalman filters; computational complexity; filtering theory; learning (artificial intelligence); neural nets; pattern classification; aerospace problem; causality index; classification; dimensionality reduction; efficient training techniques; extended Kalman filter algorithm; jitter; multidimensional input space; network decision boundary; neural network; neural network inversion; oracle query; query-based strategy; Aerospace safety; Airplanes; Error correction; Feeds; Jitter; Neural networks; Neurons; Predictive models; Real time systems; Software safety;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1999. IJCNN '99. International Joint Conference on

Conference_Location

Washington, DC

ISSN

1098-7576

Print_ISBN

0-7803-5529-6

Type

conf

DOI

10.1109/IJCNN.1999.831156

Filename

831156