Re: RBF Toolbox?

[Mike B.]

Hi Jordi,

Thanks for the prompt reply. 
I am interested in interpolation from scattered data, dimension (number of 
components per vector) can be as high as 200. Ideally, the toolbox would allow 
to select from several types (multiquadric, linear, Gaussian, inverse 
multiquadric etc.) and would calibrate any hyper-parameters (such as the free 
coefficient in MQ and IMQ), say, by cross-validation. The DACE toolbox 
calibrates the Kriging hyper-parameters by maximum likelihood.

Cheers,
Mike.



--- On Fri, 23/4/10, Jordi Gutiérrez Hermoso <address@hidden> wrote:

> From: Jordi Gutiérrez Hermoso <address@hidden>
> Subject: Re: RBF Toolbox?
> To: address@hidden
> Cc: "Octave mai. lis." <address@hidden>
> Date: Friday, 23 April, 2010, 1:39 PM
> On 22 April 2010 21:41, Mike B.
> <address@hidden>
> wrote:
> 
> > Is there an octave (or octave-compatible) toolbox for
> Radial Basis
> >Functions (RBFs)?. I am currently using the DACE
> toolbox for Kriging
> >and am looking for something similar for RBFs. Cheers,
> Mike.
> 
> No, there isn't, but I may be interested in making one. My
> MSc thesis
> work was ("is", I guess, sigh) about using RBFs for
> unsymmetric
> collocation for solving PDEs.
> 
> What are the specs? What do you expect such a toolbox to
> do? What are
> you using RBFs for? The big application for me, like I
> said, was
> collocation. What's yours?
> 
> - Jordi G. H.
>