hyperparameter tuning Flashcards
1
Q
name some hyperparameters in neural network?
A
learning rate, no of layers, no of hidden units, batch size…
2
Q
2 ways to do hyperparamters tuning?
A
try random values (dont use grid if have many hyperparams)
coarse to find: try a few to see which ranges work best then zoom in to thay range
3
Q
differences between parameters and hyperparameters?
A
params: estimated from data automatically
hyperparams: manually set, used in processes to help estimate params
