All geek questions in one place

What does the kernel scale parameter do in a linear and polynomial kernel in SVM?

I have a theoretical question and I understand the concept of a kernel scale with a Gaussian kernel, but when I run Optimize Hypermeters in fitcsvm in Matlab, it gives me different values ​​than one, and I would like to understand what that means ...

What does the high value of the kernel scale in the svm linear kernel mean? and in polynomial?

+7
source share
1 answer

Pay attention to the following MATLAB help items:

  • - - - OptimizeHyperparameters. "OptimizeHyperparameters" "-" HyperparameterOptimizationOptions.

  • OptimizeHyperparameters , , -. , OptimizeHyperparameters "auto" "auto".

MATLAB X KernelScale. . , .

KernelScale [1e-3,1e3]. Fitcsvm , - [1e-3,1e3].

KernelScale , , "KernelFunction", "kernel", . .

0

Source: https://habr.com/ru/post/1015880/

More articles:


All Articles