In a Denoising Diffusion Probabilistic Model (DDPM), the sampling process works by running the reverse diffusion steps:
Are these reverse steps in DDPM usually stochastic (i.e., involve random noise at each step) rather than purely deterministic?
Correct
Incorrect
A DDPM is trained with
time steps. If the initial time step
has a very small
(variance), and the final time step
has a very large
, what is the resulting value of the
total added noise component
at
and
?
: Close to
;
: Close to
.
: Close to
;
: Close to
.
: Close to
;
: Close to
.
: Close to
;
: Close to
.
The
is fixed because the variance is independent of the data, determined
only by the time step
.
Fixing the variance simplifies the ELBO such that the objective only needs to predict the noise, which implicitly predicts the mean.
The variance
is not fixed; the U-Net predicts both the mean
and the
variance
simultaneously.
The variance is fixed because the U-Net is designed only to denoise, not to estimate uncertainty.
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.
The IIT Madras BS Mathematical Foundations of Generative AI (Mathematical Foundations of Generative AI) Quiz 2 paper sat on 23 Nov 2025, in the September 2025 term: 15 questions for 50 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 | Mathematical Foundations of Generative AI Quiz 2 23 Nov 2025 at a glance |
|---|---|
| Term | September 2025 term |
| Subject | Mathematical Foundations of Generative AI |
| Questions | 15 |
| Marks | 50 |
| Duration | 120 min |
| MCQ | 11 |
| MSQ | 2 |
| Numerical | 2 |
| Official paper | IIT M DEGREE AN EXAM QDB2 23 Nov 2025 NEW |
| Negative marking | No negative marking. |
| Updated |
