3/21/25, 1:39 PM Introduction to Machine Learning (Tamil) - - Unit 5 - Week 3
buvaneswaricsk@gmail.com
(https://swayam.gov.in)
(https://swayam.gov.in/nc_details/NPTEL)
NPTEL (https://swayam.gov.in/explorer?ncCode=NPTEL) » Introduction to Machine Learning (Tamil) (course)
Course outline Week 3: Assignment 3
The due date for submitting this assignment has passed.
How does an NPTEL Due on 2022-02-16, 23:59 IST.
online course work?
()
Assignment submitted on 2022-02-14, 08:42 IST
Week 0 () 1) Which of the following vectors are orthogonal to the vector 1 point
1
⎡ ⎤
Week 1 ()
⎢ −1 ⎥
x = ⎢ ⎥
⎢ 2 ⎥
Week 2 () ⎣ ⎦
−2
Week 3 ()
y = [ 1 1 1 1 ]
[ ]
https://onlinecourses.nptel.ac.in/noc22_cs58/unit?unit=23&assessment=71 1/6
3/21/25, 1:39 PM Introduction to Machine Learning (Tamil) - - Unit 5 - Week 3
y = [ 2 −2 1 −1 ]
Discriminative models
(unit?
y = [ 4 4 4 4 ]
unit=23&lesson=59)
Logistic Regression y = [ 0.25 0.5 0.75 1 ]
(unit?
Yes, the answer is correct.
unit=23&lesson=60)
Score: 1
Summary and big Accepted Answers:
y = [ 1 1 ]
picture (unit? 1 1
y = [ 4 4 ]
unit=23&lesson=61) 4 4
Maximum likelihood 2) Given the learned weight vector w, select the statement that relates the line that separates the data points (i.e.,decision 1 point
estimation (unit? line) and the weight vector?
unit=23&lesson=62)
The angle between w and decision line is not 90o
Linear separability
It is always parallel to w
(unit?
unit=23&lesson=63) It can be orientated in any direction with respect to w based on the data points
It is always perpendicular to w
Perceptron and its
learning algorithm Yes, the answer is correct.
(unit? Score: 1
unit=23&lesson=64) Accepted Answers:
It is always perpendicular to w
Perceptron : A thing of
past (unit?
unit=23&lesson=65)
3) Consider the following model for binary classification 1 point
T
1, if W X > 0
p(y|X) = {
Support Vector Machine 0, W
T
X ≤ 0
(unit?
−1 0.5
unit=23&lesson=66) Suppose that a weight vector W = [ ] is given.Then the data point X = [ ] belongs to?
1 1
Optimizing weights
(unit? Negative class, (i.e., y=0)
unit=23&lesson=67) Positive class, (i.e., y=1)
Handling Outliers (unit? The point can’t be classified
unit=23&lesson=68) Yes, the answer is correct.
Dual Formulation (unit?
unit=23&lesson=69)
S
https://onlinecourses.nptel.ac.in/noc22_cs58/unit?unit=23&assessment=71 2/6
3/21/25, 1:39 PM Introduction to Machine Learning (Tamil) - - Unit 5 - Week 3
Score: 1
Kernel formulation
(unit? Accepted Answers:
unit=23&lesson=70) Positive class, (i.e., y=1)
Quiz: Week 3: 4) Suppose the Perceptron model is used for a binary classification problem. Suppose further that all the data points in the 1 point
Assignment 3 data set are correctly classified for some w.Then using the Perceptron learning algorithm to update the w will no longer modify the
(assessment? elements in the w. The statement is
name=71)
Always False
Week 3 Feedback :
Always True
Introduction to Machine
Learning (Tamil) (unit? Not always True
unit=23&lesson=27)
Yes, the answer is correct.
Score: 1
Week 4 ()
Accepted Answers:
Always True
Download Videos ()
5) Consider the follwing table, where x 1 and x 2 are features and y is a label 2 points
Lecture notes ()
Live Sessions ()
Assume that the elements in w are initialized to zero and perceptron learning algorithm is used to update the weights w. If the
learning algorithm runs for long enough iterations, then
The algorithm converges after some iterations
The algorithm never converges
The classification error becomes zero eventually
The classification error remains greater than zero
Yes, the answer is correct.
https://onlinecourses.nptel.ac.in/noc22_cs58/unit?unit=23&assessment=71 3/6
3/21/25, 1:39 PM Introduction to Machine Learning (Tamil) - - Unit 5 - Week 3
Score: 2
Accepted Answers:
The algorithm converges after some iterations
The classification error becomes zero eventually
6) Suppose that we are given a dataset for a binary classification problem with m data points. Half of the data points 1 point
belong to the positive class (i.e., y = 1) and the rest of the data points belong to the negative class(i.e., y = −1 .) Somehow, we
learned that the data points are not linearly separable. Then the statement: ”Using perceptron algorithm to classify the data points
with zero error is not possible” is?
True
False
Yes, the answer is correct.
Score: 1
Accepted Answers:
True
7) Which of the following algorithms can be used for binary classification problem? 1 point
Naive Bayes
Logistic Regression
Support Vector Machine
Perceptron
Yes, the answer is correct.
Score: 1
Accepted Answers:
Naive Bayes
Logistic Regression
Support Vector Machine
Perceptron
8) The Sigmoid function is a probabilistic function and hence the output is always between (0, 1). The statement is 1 point
True
False
https://onlinecourses.nptel.ac.in/noc22_cs58/unit?unit=23&assessment=71 4/6
3/21/25, 1:39 PM Introduction to Machine Learning (Tamil) - - Unit 5 - Week 3
Yes, the answer is correct.
Score: 1
Accepted Answers:
True
9) The diagram shown below contains data points for two classes. The blue points belong to the positive class and the 1 point
green points belong to the negative class. Assume that a linear model found a line that separates these data points as shown in the
figure. Then the classification error will be (i.e., count of number of misclassified data points)?
1
3
5
7
Yes, the answer is correct.
Score: 1
Accepted Answers:
5
https://onlinecourses.nptel.ac.in/noc22_cs58/unit?unit=23&assessment=71 5/6
3/21/25, 1:39 PM Introduction to Machine Learning (Tamil) - - Unit 5 - Week 3
https://onlinecourses.nptel.ac.in/noc22_cs58/unit?unit=23&assessment=71 6/6
