DocumentCode :
3141483
Title :
Self-organized classification problem solving with yprel neural networks
Author :
Stocker, Emmanuel ; Ribert, Arnaud ; Lecourtier, Yves
Author_Institution :
Lab. PSI-LA3i, Rouen Univ., Mont-Saint-Aignan, France
fYear :
1999
fDate :
20-22 Sep 1999
Firstpage :
390
Lastpage :
393
Abstract :
This paper deals with a new scheme of distributed classifier based on a particular formal neuron named “yprel”. The main characteristics of the proposed approach are: (i) a classifier is a set of interconnected and cooperating networks, (ii) the distributed resolution strategy emerges from the individual network classification behaviors during the incremental building phase of the classifier; (iii) each neuron is able to come to classification decisions about some elements and to communicate them; (iv) the network architectures and the interconnexion links between the networks are not a priori chosen, but get themselves organized thanks to an incremental and competitive learning between the decision-making neurons
Keywords :
distributed decision making; neural nets; pattern classification; problem solving; self-adjusting systems; unsupervised learning; classification decisions; competitive learning; cooperating networks; decision-making neurons; distributed classifier; distributed resolution strategy; formal neuron; incremental building phase; incremental learning; interconnected networks; interconnexion links; network architectures; network classification behaviors; self-organized classification problem solving; yprel neural networks; Decision making; Electronic mail; Encoding; Feature extraction; NIST; Neural networks; Neurons; Pattern recognition; Problem-solving; Read only memory;
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.1999.791806
Filename :
791806
Link To Document :
بازگشت