\input zb-basic
\input zb-ioport
\iteman{io-port 06113285}
\itemau{Zhao, Jianwei}
\itemti{Functional data learning by Hilbert feedforward neural networks.}
\itemso{Math. Methods Appl. Sci. 35, No. 17, 2111-2121 (2012).}
\itemab
Summary: This paper focuses on learning algorithms for approximating functional data that are chosen from some Hilbert spaces. An effective algorithm, called Hilbert parallel overrelaxation backpropagation (HPORBP) algorithm, is proposed for training the Hilbert feedforward neural networks that are extensions of feedforward neural networks from Euclidean space $\Bbb R^n$ to some Hilbert spaces. Furthermore, the convergence of the iterative HPORBP algorithm is analyzed, and a deterministic convergence theorem is proposed for the HPORBP algorithm on the basis of the perturbation results of Mangasarian and Solodov. Some experimental results of learning functional data on some Hilbert spaces illustrate the convergence theorem and show that the proposed HPORBP algorithm has a better accuracy than the Hilbert backpropagation algorithm.
\itemrv{~}
\itemcc{}
\itemut{functional data; feedforward neural network; learning algorithm; convergence; Hilbert parallel overrelaxation backpropagation algorithm}
\itemli{doi:10.1002/mma.2641}
\end