0
$\begingroup$

I am going to use LIBSVM for classification of data that uses a 'feature window'. Currently my data is in the form of a M x N x 3 matrix - M instances, N features and for each feature I'm considering the previous, current and next instance. If I were to only consider one instance per feature, I would simply feed the algorithm a list of instances described by N values, but in my case, each value is a 3-tuple.

Should I simply flatten all feature windows and use a M x 3N matrix? Would that have any impact on the learning process?

$\endgroup$
0
$\begingroup$

If you want to use a kernel that's built-in then you're effectively looking at a vector, and you need to flatten your data. If you want to use a special kernel, you can provide it a pre-computed kernel matrix. Note that in this case, it will output the model for you, and you'll have to use that model externally to do the kernel computations for evaluating new points (i.e., outside the training data).

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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