Deep Learning Practice · End Term · 13 Sept 2026 · May 2026 term · Set S2

Question 25: Which of the following statements about the ResNet archi…

Question 25

+2 marksOne or more correct options

Which of the following statements about the ResNet architecture and its standard training recipe are correct?

Select all that apply.

A
Dropout is applied after every residual block as the primary regularizer.
B
Batch Normalization is applied after every convolutional layer.
C
The identity shortcut connection lets gradients bypass the weight layers, helping mitigate vanishing gradients in very deep networks.
D
A global average pooling layer is used after the final convolutional stage, so the network has no large fully-connected layers other than the final classifier (FC-1000).

Show answer

Correct answers

B
Batch Normalization is applied after every convolutional layer.
C
The identity shortcut connection lets gradients bypass the weight layers, helping mitigate vanishing gradients in very deep networks.
D
A global average pooling layer is used after the final convolutional stage, so the network has no large fully-connected layers other than the final classifier (FC-1000).

See the whole paper Take it as a mock test

Question 25 of 31 in the IIT Madras BS Deep Learning Practice (Deep Learning Practice) End Term paper sat on 13 Sept 2026, in the May 2026 term (Deep Learning Practice 13 Sep 26 (Session 2)). It carries 2 marks.

Question 25: Which of the following statements about the ResNet archi…

Question 25

More questions from this paper