Skip to content
ml-recall

#optimizer-state

1 question from Optimization & Calculus

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-checkedOptimization & Calculus

You train a network with 1,000,000 parameters. Plain SGD (no momentum) stores nothing besides the parameters and their gradients. How many extra numbers does Adam keep as optimizer state?

a whole number