Title :
Bounds on rates of variable-basis and neural-network approximation
Author :
Kurkova, V. ; Sanguineti, Marcello
Author_Institution :
Inst. of Comput. Sci., Czechoslovak Acad. of Sci., Prague, Czech Republic
fDate :
9/1/2001 12:00:00 AM
Abstract :
The tightness of bounds on rates of approximation by feedforward neural networks is investigated in a more general context of nonlinear approximation by variable-basis functions. Tight bounds on the worst case error in approximation by linear combinations of n elements of an orthonormal variable basis are derived
Keywords :
approximation theory; error analysis; feedforward neural nets; approximation rate bounds; feedforward neural networks; neural-network approximation; nonlinear approximation; orthonormal variable basis; tight bounds; variable-basis approximation; variable-basis functions; worst case error; Estimation theory; Gaussian noise; Information theory; Integral equations; Kernel; Least squares approximation; Nonlinear filters; Signal detection; Stochastic processes; Time series analysis;
Journal_Title :
Information Theory, IEEE Transactions on
