Skip to content
ml-recall

#max-norm

1 question from Training Deep Networks

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

easyAI-checkedTraining Deep Networks

Max-norm regularization caps the Euclidean length of every unit's incoming weight vector at c=2c = 2: after an update, a vector whose norm exceeds cc is rescaled to norm cc. An update leaves the weights w=(3,4)w = (3, 4). After the constraint is applied, the first weight is and the second is .

Fill in every blank (hints in the boxes). Enter moves to the next blank.