Machine Learning Techniques · End Term · Sep 2025 · AN
Machine Learning Techniques · End Term · Sep 2025 AN
← Course papers · Start practice / exam
This page contains the reliably extracted subset, not the complete original paper.
Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.
0 / 16 published solutions
Question 2 MCQ · 3.0 marks
For the polynomial kernel

the explicit feature map for the vector

is 10-dimensional. Which of the following
options is the correct transformed feature vector

?
A.
B.
C.
D.
A published solution is not available for this question yet.
Report a correction for Q2
Question 4 MCQ · 2.0 marks
Consider the following points on the real line:

We run

-means algorithm with

. The initial cluster centers are

and

Based on the above data, answer the given subquestions.
What will be the cluster means after iteration 1?
A.
B.
C.
D.
A published solution is not available for this question yet.
Report a correction for Q4
Question 5 NAT · 3.0 marks
Consider the following points on the real line:

We run

-means algorithm with

. The initial cluster centers are

and

Based on the above data, answer the given subquestions.
Find the value of the objective function

after convergence. Enter the answer correct to two decimal places.
A published solution is not available for this question yet.
Report a correction for Q5
Question 6 MCQ · 2.0 marks
Suppose we have a

prior for the parameter

. Then, the value of the maximum
likelihood estimate (MLE) is equal to the value of the maximum a posteriori (MAP) estimate.
A published solution is not available for this question yet.
Report a correction for Q6
Question 7 MCQ · 2.0 marks
Consider the following training dataset for a binary classification problem:

where

is a fixed nonzero constant and labels belong to

. Let

be the weight vector
of a linear classifier. What condition should the weight vector satisfy for the 0-1 loss to be zero on
this dataset?
A.
B.
C.
D.No such weight vector

exists.
A published solution is not available for this question yet.
Report a correction for Q7
Question 8 MCQ · 2.0 marks
A.
B.
C.
D.
A published solution is not available for this question yet.
Report a correction for Q8
Question 9 NAT · 3.0 marks

A published solution is not available for this question yet.
Report a correction for Q9
Question 10 MSQ · 3.0 marks
A.If

, and

is close to 1, then such points will not contribute
much to the update of

.
B.If

, and

is close to 0, then such points will not contribute
much to the update of

.
C.If

, and

is close to 1, then such points will not contribute
much to the update of

.
D.If

, and

is close to 0, then such points will not contribute
much to the update of

.
A published solution is not available for this question yet.
Report a correction for Q10
Question 11 NAT · 4.0 marks

A published solution is not available for this question yet.
Report a correction for Q11
Question 12 NAT · 4.0 marks
Consider an SVM classifier with separating hyperplane defined by

, where the weight
vector is

. Compute the perpendicular distance from the point

to the hyperplane. Enter your answer correct to three decimal places.
A published solution is not available for this question yet.
Report a correction for Q12
Question 13 MCQ · 3.0 marks
Consider two datasets

and

where

and

such that

and

, where

and

. The maximum number of
mistakes made by the perceptron algorithm is higher on dataset

than on dataset

.
A published solution is not available for this question yet.
Report a correction for Q13
Question 14 MSQ · 3.0 marks
In a random forest classifier with

total features, each split is chosen by evaluating a randomly
selected subset of

features. Consider how changing

affects the behavior of the forest. Which
of the following statements are correct?
A.Increasing

reduces the correlation between any two trees in the forest.
B.Decreasing

reduces the correlation between any two trees in the forest.
C.If

is too small, individual trees may underfit the data.
D.Increasing

always decreases the variance of the random forest model.
E.Decreasing

makes trees more similar to each other.
A published solution is not available for this question yet.
Report a correction for Q14
Question 15 NAT · 4.0 marks

Based on the above data, answer the given subquestions.
For input

, compute the the regression output

. Enter the answer correct to one decimal
place.
A published solution is not available for this question yet.
Report a correction for Q15
Question 16 NAT · 3.0 marks

Based on the above data, answer the given subquestions.
Suppose the target value for this input is

. Compute the squared loss

. Enter
the answer correct to two decimal places.
A published solution is not available for this question yet.
Report a correction for Q16
Question 17 MCQ · 2.0 marks
Consider the following one-dimensional dataset with binary labels

.

AdaBoost uses decision stumps as weak learners. Assume the initial distribution of the dataset
assigns equal weights to all data points, i.e.,

, for

. At iteration

,
AdaBoost chooses the decision stump

Based on the above data, answer the given subquestions.
Which point will be misclassified by the first decision stump?
A published solution is not available for this question yet.
Report a correction for Q17
Question 18 MSQ · 4.0 marks
Consider the following one-dimensional dataset with binary labels

.

AdaBoost uses decision stumps as weak learners. Assume the initial distribution of the dataset
assigns equal weights to all data points, i.e.,

, for

. At iteration

,
AdaBoost chooses the decision stump

Based on the above data, answer the given subquestions.
After AdaBoost updates the sample weights for iteration

, which pair of points will have the
smallest (and equal) weights while training the second stump

?
A published solution is not available for this question yet.
Report a correction for Q18