DocumentCode :
1577995
Title :
One more approach for designing neural network algorithms of real arguments functions approximation
Author :
Sudarikov, V.A.
Author_Institution :
Sci. Neurocomput. Centre, Acad. of Sci., Moscow, Russia
fYear :
1992
Firstpage :
334
Abstract :
The author discusses an approach to representation of functions on neural networks. The approach is based on approximation of the functions by piecewise-linear components. For a fixed value of required accuracy an analytical or numerical method can be used to find the network parameters in advance
Keywords :
function approximation; neural nets; AT neural network algorithms; functions approximation; network parameters; piecewise-linear components; Algorithm design and analysis; Approximation algorithms; Function approximation; Neural networks; Stability; Tellurium;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neuroinformatics and Neurocomputers, 1992., RNNS/IEEE Symposium on
Conference_Location :
Rostov-on-Don
Print_ISBN :
0-7803-0809-3
Type :
conf
DOI :
10.1109/RNNS.1992.268554
Filename :
268554
Link To Document :
بازگشت