Custom Loss function in support vector machine

Hi,

Does anyone know whether it's possible to use a custom loss function in support vector machine model in matlab? Any example or hint will be highly appreciated.

[Bhargavi Maganuru]

By loss function you mean objective function which needs to be minimized?

Answer 1

[Jubeyer Rahman]

yes.

[Wanxin Li]

I am having the same issue here. Could you please give some guidance on implementation? Thanks in advance.

[Jubeyer Rahman]

So far I know, this is not easily doable. And I haven't got any feedback since my last post.

But if you need it for neural network, then it is possible to customize the loss function of neural network.