SVC has C and gamma parameters ( https://scikit-learn.org/stable/auto_examples/svm/plot_rbf_parameters.html )
Are there any similar parameters for an SVR (support vector regressor) as well ?
Sergey Porotsky
Yes. For example, see, please, Matlab function fitrsvm with parameters
'BoxConstraint' (i.e. C) and 'KernelScale' (i.e. gamma).
2 votes
2 thanks
Mohsen Rezaei
It depends on SVR type you use
for example in kernel RBF ===> C, gamma, epsilon are hyper parameters.
but for kernel poly and sigmoid ======> C, gamma , epsilon, degree, coeff are hyper parameters.
For more information see the following example.
https://scikit-learn.org/stable/auto_examples/svm/plot_svm_regression.html#sphx-glr-auto-examples-svm-plot-svm-regression-py
1 votes
0 thanks
- Badges
- Science topic
More Bhaskar Tripathi's questions See All
Similar questions and discussions