Based on Freed-forward Neural Networks, we develop a new method to approximate curves contained on the given surface; the main contribution is to convert the problems of space curve approximation on surfaces into the plane curve approximation by point projection. The final approximation curve restricted on the surface is achieved via the intersection of surface and cylinder whose directrix is p...

To approximate the multivariate functions with spatial inhomogeneity, in this paper we proposed an ortho-ridgelet neural network (ORNN) model. By taking orthonormal ridgelet, which is a “true” ridgelet function different with the “classic” ridgelet, as the activation function of the hidden neurons, the network is characterized of more efficient representation of a set of functions with linear a...

Control A. Carlevarino, R. Martinotti, G. Metta and G. Sandini Lira Lab – DIST – University of Genova Via Opera Pia, 13 – 16145 Genova, Italy E-mail: [email protected] Abstract This paper describes a novel network model, which is able to control its growth on the basis of the approximation requests. Two classes of self-tuning neural models are considered; namely Growing Neural Gas (GNG) a...

This work studies some of the approximating properties of feedforward neural networks as a function of the number of nodes. Two cases are considered: sigmoidal and radial basis function networks. Bounds for the approximation error are given. The methods through which we arrive at the bounds are constructive. The error studied is the L1 or sup error.

A feedforward Sigma-Pi neural network with a single hidden layer of m neurons is given by mSigma(j=1) cjg (nPi(k=1) xk-thetak(j)/lambdak(j)) where cj, thetak(j), lambdak are elements of R. In this paper, we investigate the approximation of arbitrary functions f: Rn-->R by a Sigma-Pi neural network in the Lp norm. An Lp locally integrable function g(t) can approximate any given function, if and ...

this paper investigates the performances of artificial neural networks approximation, the translog and the fourier flexible functional forms for the cost function, when different production technologies are used. using simulated data bases, the author provides a comparison in terms of capability to reproduce input demands and in terms of the corresponding input elasticities of substitution esti...

If both Reference Station (RS) and navigational device in Differential Global Positioning System (DGPS) receive signals from the same satellite, RS Position Components Error (RPCE) can be used to compensate for navigational device error. This research used hybrid method for RPCE prediction which was collected by a low-cost GPS receiver. It is a combination of Genetic Algorithm (GA) computing an...