Maximum number of features for SVM

Question

I am trying to analyse sound with SVM.

Since sound is split in huge number of digital data, I want to split the sound up into every single second.

If sample rate of sound is 44100Hz, I will get 44100 features.

Is it possible to put 44100 features in SVM?

What would be the maximum number of features for SVM?

Answer 1

It is possible to have a lot more features than what you need. I don't think there is a hard limit and the maximum number depends mostly on the resources you have(CPU, RAM) to process the data. However most often in is not a good idea to have many features. The problem is that the more features you have the more data you need to train the model in order to avoid over fitting to the train data.