DocumentCode :
3630288
Title :
Neuronal groups and interrelations
Author :
Michal Pryczek
Author_Institution :
Institute of Computer Science, Technical University of Lodz, Wolczanska 215, 90-924, Poland
fYear :
2008
Firstpage :
221
Lastpage :
227
Abstract :
Recent development of various domains of Artificial Intelligence including Information Retrieval and Text/Image Understanding created demand on new, sophisticated, contextual methods for data analysis. This article formulates Neuronal Group and Extended Neuron Somatic concepts that can be vastly used in creating such methods. Neural interrelations are described using graphs, construction of which is done in parallel with neural network learning. Prototype technique based on Growing Neural Gas is also presented to give more detailed view.
Keywords :
"Pattern recognition","Extraterrestrial measurements","Kernel","Computer science","Information retrieval","Image retrieval","Prototypes","Pattern analysis","Feature extraction","Information technology"
Publisher :
ieee
Conference_Titel :
Computer Science and Information Technology, 2008. IMCSIT 2008. International Multiconference on
Print_ISBN :
978-83-60810-14-9
Type :
conf
DOI :
10.1109/IMCSIT.2008.4747243
Filename :
4747243
Link To Document :
بازگشت