Tag Info

1

This isn't surprising. A model with more features has a richer space of functions to approximate as compared to a function with fewer features. Feature selection, in my own opinion, is not about increasing performance. On the contrary, it is about finding a set of features which does good enough as compared to the model with the full set. I wrote a small ...

1

Imposing a maximum length over the strings and the size of the alphabet, we could form a feature matrix, $\phi(x)$ where each element is binary indicating the existence of the substring in $x$. For example, if the alphabet is lowercase english letters, the first $26$ elements will be for checking the existence of one-letter words, i.e. $a,b,...,z$, and the ...

1

There are basically two problems: As Patrick said, your range of C-values doesn't make much sense; but, more importantly The default metric used by GridSearchCV, the accuracy, is not suitable for what you're trying to do: minimise the number of support vectors while keeping the optimal performance (nor is any other of the metrics provided in sklearn, btw.). ...

1

Some thoughts on your interesting question: Good features are problem dependent. So seems difficult (if possible) to incorporate feature engineering into any rigorous mathematical framework. To me, pushing the problem of finding good features to finding good kernels is a way to separate the problem in two parts. First, the mathematics (learning from good/...

Only top voted, non community-wiki answers of a minimum length are eligible