DocumentCode :
3214105
Title :
An efficient finite precision RBF-M neural network architecture using support vectors
Author :
Dogaru, Radu ; Dogaru, Ioana
Author_Institution :
Dept. of Appl. Electron. & Inf. Eng., Univ. Politeh. of Bucharest, Bucharest, Romania
fYear :
2010
fDate :
23-25 Sept. 2010
Firstpage :
127
Lastpage :
130
Abstract :
This paper investigates the effects of using limited precision for efficient implementations of the RBF-M neural network. This architecture employs only simple arithmetic operators and is characterized by simple LMS training in an expanded feature space generated by RBF functions centered around support vectors selected via a simple algorithm. The classification performances of our low complexity, finite precision architecture are similar and even better to those obtained using the more complex SVM.
Keywords :
radial basis function networks; support vector machines; RBF-M neural network; modified radial basis function networks; support vector machines; Artificial neural networks; Classification algorithms; Complexity theory; Computer architecture; Kernel; Support vector machines; Training; VLSI; fixed point; kernel neural network; radial basis function;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Network Applications in Electrical Engineering (NEUREL), 2010 10th Symposium on
Conference_Location :
Belgrade
Print_ISBN :
978-1-4244-8821-6
Type :
conf
DOI :
10.1109/NEUREL.2010.5644089
Filename :
5644089
Link To Document :
بازگشت