A radial basis function network (RBFN) for function approximation

Otro

Registro en:

42nd Midwest Symposium on Circuits and Systems, Proceedings, Vols 1 and 2. New York: IEEE, p. 1099-1101, 1999.

http://hdl.handle.net/11449/130589

http://acervodigital.unesp.br/handle/11449/130589

10.1109/MWSCAS.1999.867828

WOS:000089525800262

2-s2.0-0033292531

http://dx.doi.org/10.1109/MWSCAS.1999.867828

http://repositorioslatinoamericanos.uchile.cl/handle/2250/941132

Autor

Lucks, M. B.

Oki, N.

RamirezAngulo, J.

Institución

Universidade Paulista Júlio de Mesquita Filho (Brasil)

Resumen

A radial basis function network (RBFN) circuit for function approximation is presented. Simulation and experimental results show that the network has good approximation capabilities. The RBFN was a squared hyperbolic secant with three adjustable parameters amplitude, width and center. To test the network a sinusoidal and sine function,vas approximated.

Materias

Approximation theory

Bipolar transistors

Computer simulation

Electric network analysis

Function evaluation

Neural networks

Simulated annealing

Function approximation

Radial basis function network

Sinusoidal function

Integrated circuit testing

Mostrar el registro completo del ítem