Title :
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
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;
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
DOI :
10.1109/ICSMC.1993.385056
