When I run a dataset using Support Vector Machines(SVM) and I am use both Polynomial and Linear Kernels. The performance I obtain is different, so I was wondering if there is any information I can obtain about the data from how it performs on each kernel.

Or phrased in a different way, what kind of data tends to perform better with a Polynomial Kernel vs a Linear Kernel and vice versa.

what kind of data tends to perform better with a Polynomial Kernel vs a Linear Kernel

Polynomial kernel is more suitable nonlinear inseparable data, linear kernel is more suitable linear separable data.

Before choosing the kernel, you can visualize the training data, make sure the linear kernel is enough.

Your Answer

 
discard

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Not the answer you're looking for? Browse other questions tagged or ask your own question.