Login to manage your account

Please enter a valid email address.
Forgot Password?
Please enter a valid password.
OR

Don't have an account yet? Sign up

What does the learning rate control in gradient descent?

  1. A The size of the step taken towards the loss minimum on each update
  2. B The number of training examples used
  3. C The number of layers in the network
  4. D The regularisation strength
Answer

The size of the step taken towards the loss minimum on each update

Too high and training diverges or oscillates; too low and it converges slowly or stalls in a poor region.

All Machine Learning MCQs

Login to manage your account

Please enter a valid email address.
Forgot Password?
Please enter a valid password.
OR

Don't have an account yet? Sign up as