You are given a dataset of 10 \times 10 grayscale images. Your goal is to build a 5-class classifier. You have to adopt one of the following two options: - Model A: the input is flattened into a 100-dimensional vector, followed by a fully-connected layer with 5 neurons without bias - Model B: the input is directly given to a convolutional layer with five 10 \times 10 filters Suppose you make your choice on the basis of the number of parameters in the models, p_A = number of parameters in ModelA, and similarly let p_B = number of parameters in ModelB.

(A) Option figure from the original question paper

(B) Option figure from the original question paper

(C) Option figure from the original question paper

(D) Option figure from the original question paper

Deep Learning End Term: 22 December 2024 (September 2024 term)

Question 1

+2 marksOne correct option

Question 2

+2 marksOne correct option

You are given a dataset of $10 \times 10$ grayscale images. Your goal is to build a 5-class classifier. You have to adopt one of the following two options:

Model A: the input is flattened into a 100-dimensional vector, followed by a fully-connected layer with 5 neurons without bias
Model B: the input is directly given to a convolutional layer with five $10 \times 10$ filters

Suppose you make your choice on the basis of the number of parameters in the models, $p_A$ = number of parameters in ModelA, and similarly let $p_B$ = number of parameters in ModelB.

Question 3

+2 marksOne correct option

In the context of RNNs, what structural feature of LSTMs helps reduce the impact of vanishing gradients?

A
Skip connections
B
Gated mechanisms like forget and input gates
C
Weight sharing across layers
D
Use of dropout

18 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 End Term 22 Dec 2024 paper

The IIT Madras BS Deep Learning (Deep Learning) End Term paper sat on 22 Dec 2024, in the September 2024 term: 21 questions for 50 marks in 180 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 End Term 22 Dec 2024 at a glance
Term	September 2024 term
Subject	Deep Learning
Course code	BSCS3004
Questions	21
Marks	50
Duration	180 min
MCQ	10
Numerical	10
MSQ	1
Official paper	IIT M DEGREE AN EXAM QDB3 22 Dec 2024
Negative marking	No negative marking.
Updated	25 Sept 2026

Deep Learning End Term: 22 December 2024 (September 2024 term)

Question 1

Question 2

Question 3

18 more questions in this paper

More on the Deep Learning End Term 22 Dec 2024 paper

Same End Term, other subjects

More Deep Learning