Skip to content
ml-recall

#loss-landscape

2 questions from Optimization & Calculus, Training Deep Networks

Timed test

2 questions · 2 min · score and explanations at the end

Take a test
Q 1 / 2Score 0 / 0

Question 1: Short answer

easyAI-checkedOptimization & Calculus

An MLP has one hidden layer with 5 units and a single output. Starting from one trained set of weights, how many weight settings (counting the original) can you get just by reordering the hidden units, all computing exactly the same function? Assume no two hidden units are identical.

a whole number