DocumentCode :
3140884
Title :
Designing efficient distributed neural classifiers: application to handwritten digit recognition
Author :
Ribert, Arnaud ; Lecourtier, Yves ; Ennaji, Abdel
Author_Institution :
Fac. des Sci., Rouen Univ., Mont-Saint-Aignan, France
fYear :
1999
fDate :
20-22 Sep 1999
Firstpage :
265
Lastpage :
268
Abstract :
Describes an automatic method for building distributed neural classifiers for pattern recognition. The methodology is based on the detection of reliable regions in the representation space, i.e. clusters exclusively composed of patterns from the same class. This detection is performed using a hierarchical clustering method associated with the supervised information provided by a professor. The proposed methodology consists of associating each of these regions with a multilayer perceptron (MLP) which has to recognise elements that are inside its region while rejecting all others. Experimental results for a real problem (handwritten digit recognition) reveal an interesting generalisation behaviour of the distributed classifier in comparison to the k-nearest neighbour algorithm as well as a single MLP
Keywords :
generalisation (artificial intelligence); handwritten character recognition; multilayer perceptrons; pattern classification; pattern clustering; distributed neural classifiers; generalisation behaviour; handwritten digit recognition; hierarchical clustering method; k-nearest neighbour algorithm; multilayer perceptron; reliable region detection; representation space; supervised information; Buildings; Handwriting recognition; Humans; Identity-based encryption; Multi-layer neural network; Multilayer perceptrons; Neural networks; Nonhomogeneous media; Pattern recognition; Spatial databases;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Document Analysis and Recognition, 1999. ICDAR '99. Proceedings of the Fifth International Conference on
Conference_Location :
Bangalore
Print_ISBN :
0-7695-0318-7
Type :
conf
DOI :
10.1109/ICDAR.1999.791775
Filename :
791775
Link To Document :
بازگشت