Question 1
Consider the following code snippet:
Based on the standard normalization technique for a single-channel grayscale image dataset like FashionMNIST, which of the following correctly fills in blank (A)?
Question 2
Suppose during training Epoch 1 D(real)=0.90 D(fake)=0.10 Later Epoch 20 D(real)=0.999 D(fake)=0.0001
What problem is most likely? (Here, D(x) represents Discriminator's output on image x)
Discriminator has become too strong, leading to vanishing gradients for the generator.
Mode collapse has definitely occurred.
Generator has perfectly learned the data distribution.
The discriminator will stop updating permanently.
Question 3
Let D(x) denote the discriminator's output. Which of the following represents the most desirable discriminator output during stable GAN training?
D(real) = 0.9, D(fake) = 0.1
D(real) = 0.8, D(fake) = 0.2
D(real) = 1.0, D(fake) = 0.0
D(real) = 0.5, D(fake) = 0.5
16 more questions in this paper
Sign in with Google — it is free — to see every question with its answer and explanation, practise it in learning mode, or take it as a timed mock test.
More on the Deep Learning and GenAI Quiz 2 16 Aug 2026 paper
The IIT Madras BS Introduction to Deep Learning and Generative AI (Deep Learning and GenAI) Quiz 2 paper sat on 16 Aug 2026, in the May 2026 term: 19 questions for 47 marks in 120 minutes. The first 3 questions are below. Sign in with Google — it is free — to see the whole paper with its answers and explanations, in learning mode or as a timed mock test.
| Feature | Deep Learning and GenAI Quiz 2 16 Aug 2026 at a glance |
|---|---|
| Term | May 2026 term |
| Subject | Introduction to Deep Learning and Generative AI |
| Course code | BSDA2001 |
| Questions | 19 |
| Marks | 47 |
| Duration | 120 min |
| MCQ | 10 |
| MSQ | 6 |
| Numerical | 3 |
| Official paper | Introduction To Deep Learning And Generative Ai 14 Aug 26 |
| Negative marking | No negative marking. |
| Updated |