DocumentCode :
2329857
Title :
Clustering with minicolumnar receptive field self-organization
Author :
Lücke, Jörg
Author_Institution :
Inst. fur Neuroinformatik, Ruhr-Univ. Bochum, Germany
Volume :
4
fYear :
2004
fDate :
25-29 July 2004
Firstpage :
3113
Abstract :
We study clustering, i.e., unsupervised data classification, by a model of the cortical macrocolumn. Continuous valued input vectors are encoded using a population place code. The macrocolumn model self-organizes its minicolumnar receptive fields (RFs) such that the input is hierarchically subdivided into increasingly finer classes. If input superpositions are used for training, the system is able to find an appropriate classification of the input and a suitable representation of input superpositions. Together with fast reaction times the model satisfies major requirements of biological information processing and distinguishes itself from other suggested models of continuous value processing in biological neural networks.
Keywords :
learning (artificial intelligence); neural nets; neurophysiology; pattern clustering; visual databases; biological information processing; biological neural networks; cortical macrocolumn; minicolumnar receptive field self-organization; population place code; unsupervised data classification; Artificial neural networks; Biological information theory; Biological neural networks; Biological system modeling; Biology computing; Databases; Electronic mail; Encoding; Information processing; Neurons;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
Conference_Location :
Budapest
ISSN :
1098-7576
Print_ISBN :
0-7803-8359-1
Type :
conf
DOI :
10.1109/IJCNN.2004.1381170
Filename :
1381170
Link To Document :
بازگشت