Cooperation and modularity for classification through neural network techniques

Author

Dorizzi, Bernadette ; Auger, Jean-Marie ; Sebire, Philippe

Author_Institution

Inst. Nat. des Telecommun., Evry, France

fYear

1993

fDate

17-20 Oct 1993

Firstpage

469

Abstract

We study modularity in the frame of neural network systems on two real-size applications. The cooperation of performant modules is used to improve recognition and rejection rates of handwritten digits coming from postal zip-codes. From a multi-class problem in multi-font character recognition, we have designed 49 neural submodules (one per class), and different cooperation schemes are studied and compared. The relation between the quality of the expert system and the efficiency of the cooperation scheme is shown

Keywords

character recognition; cooperative systems; expert systems; image classification; neural nets; cooperation scheme; efficiency; expert system; handwritten digit recognition; modularity; multi-class problem; multi-font character recognition; neural network; Character recognition; Handwriting recognition; Learning systems; Multilayer perceptrons; Neural networks; Neurons; Optical character recognition software; Optical sensors; Partitioning algorithms; Statistics;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 1993. 'Systems Engineering in the Service of Humans', Conference Proceedings., International Conference on

Conference_Location

Le Touquet

Print_ISBN

0-7803-0911-1

Type

conf

DOI

10.1109/ICSMC.1993.385056

Filename

385056