Title :
The role of the RKH space F in the analysis and design of recurrent neural networks
Author :
de Figueiredo, Rui J.P.
Author_Institution :
Henry Samueli Sch. of Eng., California Univ., Irvine, CA, USA
fDate :
31 July-4 Aug. 2005
Abstract :
The space F(H), or simply F, is a reproducing kernel Hilbert space (RKHS) of analytic (nonlinear) functional (Volterra functional) on a separable Hilbert space H. It was introduced in the late 1970´s by the author, in collaboration with T.A.W. Dwyer, III, and L. Zyla, to represent input-output maps of large scale nonlinear dynamical systems. In the present paper we show how the properties of F, and, in particular, its reproducing kernel, can be used to model the structure and behavior of recurrent neural networks (RNNs).
Keywords :
Hilbert spaces; functional analysis; recurrent neural nets; analytic Volterra functional; large scale nonlinear dynamical system; nonlinear Volterra functional; recurrent neural network analysis; reproducing kernel Hilbert space; Competitive intelligence; Computational intelligence; Finite impulse response filter; Hilbert space; IIR filters; Intelligent networks; Kernel; Recurrent neural networks; Signal analysis; Signal design;
Conference_Titel :
Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on
Print_ISBN :
0-7803-9048-2
DOI :
10.1109/IJCNN.2005.1556093
