Skip to main content
ScienceVerse

← Back to Gradient descent

Gradient descent quick check

A quick check of 3 questions. After you submit, each question shows the right answer and why.

3 of 12 questions, Advanced level. Aimed at the Advanced level, your current depth. Questions you have not answered yet come first.

Show all 12 questions

ScientistQuestion 1 of 3

The simulation's 'small steps' preset runs gradient descent on f(x) = x² from x = 10 with learning rate 0.1 for 20 steps. What is x at the end? (3 decimal places)

AdvancedQuestion 2 of 3

What does stochastic gradient descent use instead of the gradient over the entire training set?

AdvancedQuestion 3 of 3

For many classes of high-dimensional functions, local minima are more common than saddle points.