Title :
Radial basis function networks with quantized parameters
Author :
Lucks, Marcio B. ; Oki, Nobuo
Author_Institution :
UNESP (Univ. Estadual Paulista), Ilha Solteira
Abstract :
A RBFN implemented with quantized parameters is proposed and the relative or limited approximation property is presented. Simulation results for sinusoidal function approximation with various quantization levels are shown. The results indicate that the network presents good approximation capability even with severe quantization. The parameter quantization decreases the memory size and circuit complexity required to store the network parameters leading to compact mixed-signal circuits proper for low-power applications.
Keywords :
function approximation; radial basis function networks; parameter quantization; quantized parameters; radial basis function networks; sinusoidal function approximation; Artificial neural networks; Circuit simulation; Computational modeling; Computer networks; Computer simulation; Function approximation; Hardware; Parallel processing; Quantization; Radial basis function networks; Function Approximation; Quantized Parameters; Radial Basis Function Network;
Conference_Titel :
Computational Intelligence for Measurement Systems and Applications, 2008. CIMSA 2008. 2008 IEEE International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4244-2305-7
Electronic_ISBN :
978-1-4244-2306-4
DOI :
10.1109/CIMSA.2008.4595826
