Who is afraid of the big bad ANN?

Author

Boger, Zvi

Author_Institution

Licensing & Safety Div., Israeli Atomic Energy Comm., Beer-Sheva, Israel

Volume

3

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

2000

Lastpage

2005

Abstract

The author\´s ten-year experience with training large-scale ANN models with the PCA-CG algorithm that generates a non-random initial connection weight set is presented. The suggested small number of hidden neurons and automatic identification and removal of the less relevant inputs increases the robustness of these models. Examples of ANN modeling of "artificial nose" sensor array, TV program rating and e-mail letter importance classification demonstrate the algorithm efficiency

Keywords

classification; intelligent sensors; learning (artificial intelligence); neural nets; principal component analysis; PCA CG algorithm; TV program rating prediction; artificial nose sensor array; e-mail letter importance classification; hidden neurons; large-scale neural networks; learning process; local minima; nonrandom initial connection weight; principal component analysis; training; Artificial neural networks; Chemical technology; Industrial training; Large-scale systems; Licenses; Neurons; Robustness; Safety; Sensor arrays; Speech analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1007444

Filename

1007444