Deep Learning Quiz 1: 23 February 2025 (January 2025 term)

1. A

   Momentum uses the current gradient to update the velocity, while NAG uses a lookahead gradient based on a tentative future position.

2. B

   Momentum is computationally faster than NAG because it skips calculating the gradient at a lookahead position.

3. C

   NAG is a variant of momentum that adjusts the step size dynamically during training.

4. D

   Momentum uses an adaptive learning rate, whereas NAG uses a fixed learning rate.

1. A

2. B

3. C

4. D

Select all that apply.

1. A

   The weight update is tiny at a gentle loss surface.

2. B

   The weight update is tiny at a steep loss surface.

3. C

   The weight update is large at a steep loss surface.

4. D

   The weight update is large at a gentle loss surface.