Re: what is SVM? what are the good features of SVM?

Aleks Jakulin wrote:
> "walala" <[EMAIL PROTECTED]> wrote:
>
> > I saw a lot buzzword about SVM? What is it? And why is it hot? Can
> > it be used for curve fitting/extrapolate/prediction problem?
>
>
> SVM is hot because you can use relatively robust quadratic programming
> optimization apparatus instead of the incremental back-propagation
> most people use for neural networks: 
Dear Aleks

It is sad peoples are stuck with Back Prop!!

Anyways, we need very good Nonlinear Programming Optimization Methods 
when we tackle NN in general.

As you point out here, Quadratic Programming for which there have been 
good fast codes for some time are a hallmark of SVM.

As an aside, what is the current status of SVM. One of the criticisms I 
heard a while back was the need for a lot of support vectors to get 
reasonable answers.

I don't use SVM per se but do use kernel methods and I agree these 
approaches are powerful.

Paul


there are very few parameters
> that you need to set, and even if you don't set them, it's likely to
> work. Furthermore, the whole methodology is a bit more rigorous
> mathematically. Finally, the tools are simple and accessible.
>
> RBF kernels are just one of a large set of available kernels for SVM.
> There are linear ones, polynomial ones, or even adaptive ones.
>
> Aleks