Exercise

How Many Models?

Adding more hyperparameters or values, you increase the amount of models created but the increases is not linear it is proportional to how many values and hyperparameters you already have.

How many models would be created when running a grid search over the following hyperparameters and values for a GBM algorithm?

learning_rate = [0.001, 0.01, 0.05, 0.1, 0.2, 0.3, 0.5, 1, 2]
max_depth = [4,6,8,10,12,14,16,18, 20]
subsample = [0.4, 0.6, 0.7, 0.8, 0.9]
max_features = ['auto', 'sqrt', 'log2']

These lists are in your console so you can utilize properties of them to help you!

Instructions

50 XP

Possible Answers

26
9 of one model, 9 of another
1 large model
1215

Take Hint (-15 XP)