Basically it means that we train the model on the training set. And obtain some function whose accuracy we can calculate. Now using this function we obtain the results on the test set.

Featured Contributions

reply in this discussion

Basically it means that we train the model on the training set. And obtain some function whose accuracy we can calculate. Now using this function we obtain the results on the test set.

Read more… (33 words)

reply in this discussion

Can you please explain this in more detail.

An interesting property of L1 regularization is that model's parameters become sparse during optimization, i.e. it promotes a larger number of parameters w to be zero. This is because smaller weights are equally penalized as larger weights, whereas in L2 regularizations, larger weights are being penalized much more. This sparse property is often quite useful.

How are larger weights more penalised in L2 and how do large number of weights in L1 go to zero

Read more… (83 words)