Plot of train and test regularized loss curves against f(lambda) for ridge regression, with the question text

(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

Hard-margin SVM diagram with decision boundary w^Tx = 0, supporting hyperplanes w^Tx = 1 and w^Tx = -1, weight vector w and test points x1, x2, with the question text

(A) The predicted labels for x1 and x2 are 1 and −1 respectively.

(B) The predicted labels for x1 and x2 are −1 and 1 respectively.

(C) The predicted label for both data-points is 1.

(D) The predicted label for both data-points is −1.

Figure from the original question paper

(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

Figure from the original question paper

(A) The dataset is linearly separable with a positive margin.

(B) The perceptron algorithm will terminate after a finite number of iterations when trained on this dataset.

(C) The dataset is linearly separable, but the margin may be zero.

(D) The dataset is not linearly separable.

Figure from the original question paper

(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

Plot of four convex surrogate loss functions for the 0-1 loss Based on the above data, answer the given subquestions. Figure from the original question paper

(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

Figure from the original question paper

(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

May 2024 term · Machine Learning Techniques · BSCS2007

MLT End Term: 1 September 2024, Set QDF1 (May 2024 term)

The IIT Madras BS Machine Learning Techniques (MLT) End Term paper sat on 1 Sept 2024, in the May 2024 term, set QDF1: 30 questions for 50 marks in 180 minutes. Every question is below with its answer. Take it as a timed mock test to be marked, or read it through first.

Questions: 30
Marks: 50
Duration: 180 min
MCQ: 13
Numerical: 14
MSQ: 3

Take as mock test Practise with answers

Updated 25 Sept 2026

Official paper: IIT M FOUNDATION DIPLOMA AN EXAM QDF3 01 Sep 2024 · No negative marking.

Question 1

+3 marksOne correct option

A
80%
B
60%
C
20%
D
15%

Show answer

Correct answer

A
80%

Question 1 on its own page

Question 2

+3 marksOne correct option

Show answer

Correct answer

Question 2 on its own page

Question 3

+3 marksOne correct option

Match the characteristics given below with the appropriate ensemble technique.
1. Decision stumps
2. Deep decision trees
3. Parallel execution
4. Sequential execution

A
Bagging → (2), (3); Boosting → (1), (4)
B
Bagging → (1), (4); Boosting → (2), (3)
C
Bagging → (1), (3); Boosting → (2), (4)
D
Bagging → (2), (4); Boosting → (1), (3)

Show answer

Correct answer

A
Bagging → (2), (3); Boosting → (1), (4)

Question 3 on its own pageAlso asked in End Term 1 Sept 2024

Question 4

+3 marksOne correct option

A
The predicted labels for x1 and x2 are 1 and −1 respectively.
B
The predicted labels for x1 and x2 are −1 and 1 respectively.
C
The predicted label for both data-points is 1.
D
The predicted label for both data-points is −1.

Show answer

Correct answer

A
The predicted labels for x1 and x2 are 1 and −1 respectively.

Question 4 on its own page

Question 5

+3 marksOne correct option

Show answer

Correct answer

Question 5 on its own page

Question 6

+3 marksOne correct option

A
2x1 + x2 = 0
B
x1 − 2x2 = 0
C
x1 + x2 = 0
D
x1 + 2x2 = 0

Show answer

Correct answer

A
2x1 + x2 = 0

Question 6 on its own page

Question 7

+3 marksNumerical answer

Show answer

Correct answer: 0.4

Question 7 on its own page

Question 8

+3 marksNumerical answer

Show answer

Correct answer: 30

Question 8 on its own page

Question 9

+3 marksNumerical answer

Show answer

Correct answer: 0.315 (accepted within ±0.055)

Question 9 on its own page

Question 10

+3 marksOne or more correct options

Select all that apply.

Show answer

Correct answers

Question 10 on its own page

Question 11

+3 marksOne or more correct options

Select all that apply.

A
The dataset is linearly separable with a positive margin.
B
The perceptron algorithm will terminate after a finite number of iterations when trained on this dataset.
C
The dataset is linearly separable, but the margin may be zero.
D
The dataset is not linearly separable.

Show answer

Correct answers

A
The dataset is linearly separable with a positive margin.
B
The perceptron algorithm will terminate after a finite number of iterations when trained on this dataset.

Question 11 on its own page

Question 12

+3 marksOne or more correct options

Select all that apply.

Show answer

Correct answers

Question 12 on its own page

Question 13

+1 markOne correct option

Based on the above data, answer the given subquestions.

The weight vector output by the perceptron algorithm on this dataset can be expressed as a linear combination of the data-points where the coefficients of the linear combination are integers.

A
TRUE
B
FALSE

Show answer

Correct answer

A
TRUE

Question 13 on its own page

Question 14

+1 markOne correct option

Based on the above data, answer the given subquestions.

A
TRUE
B
FALSE

Show answer

Correct answer

B
FALSE

Question 14 on its own page

Question 15

+1 markOne correct option

Based on the above data, answer the given subquestions.

If a soft-margin SVM is trained on this dataset, the optimal weight vector it returns will be the same as the one returned by a hard-margin SVM, irrespective of the value of the hyperparameter C.

A
TRUE
B
FALSE

Show answer

Correct answer

B
FALSE

Correct answer: 1

Question 25 on its own page

Question 26

+1 markOne correct option

Based on the above data, answer the given subquestions.

Show answer

Correct answer

Question 26 on its own page

Question 27

+1 markNumerical answer

Consider the following architecture of a neural network for a binary classification problem:

Layer type	Number of neurons
Input	5
Hidden layer-1	10
Hidden layer-2	10
Output	1

Based on the above data, answer the given subquestions.

How many learnable parameters does this network have? Ignore the biases in the computation.

Show answer

Correct answer: 160

Question 27 on its own page

Question 28

+1 markOne correct option

Consider the following architecture of a neural network for a binary classification problem:

Layer type	Number of neurons
Input	5
Hidden layer-1	10
Hidden layer-2	10
Output	1

Based on the above data, answer the given subquestions.

What is the most appropriate choice of activation function for the output layer if the binary cross- entropy loss is used?

A
Sigmoid
B
Linear
C
ReLU

Show answer

Correct answer

A
Sigmoid

Question 28 on its own page

Question 29

+1 markOne correct option

Consider the following architecture of a neural network for a binary classification problem:

Layer type	Number of neurons
Input	5
Hidden layer-1	10
Hidden layer-2	10
Output	1

Based on the above data, answer the given subquestions.

For a particular data-point, the activations after the first hidden layer in the forward pass is given to be $\begin{bmatrix} 0.2 & 0.1 & 1.5 & 0.3 & 0.1 & 0 & 0.8 & 1.2 & 1 & 0 \end{bmatrix}^T$ .

What is the activation function used in the first hidden layer?

A
ReLU
B
Sigmoid

Show answer

Correct answer

A
ReLU

Question 29 on its own page

Question 30

+2 marksOne correct option

Show answer

Correct answer

Question 30 on its own page