Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Are you looking for Deep Learning IIT Ropar Week 1 Nptel Assignment Answers ?. All weeks of Deep Learning IIT Ropar check here.
Table of Contents
Deep Learning IIT Ropar Week 1 Nptel Assignment Answers (July-Dec 2026)
Que1. What value of π correctly implements the specified alarm behavior?
a) 1
b) 2
c) 3
d) 4
Que2. Which of the following sensor activation patterns will result in an alarm signal?
Select all that apply.
a) (1, 1, 1, 0)
b) (0, 1, 1, 1)
c) (1, 0, 0, 1)
d) (1, 1, 1, 1)
e) (0, 0, 1, 1)
Que3. Fill in the blank.
The total number of sensor input combinations that trigger the alarm is: __________
Que4. Which of the following statements about the alarm logic are correct?
Select all that apply.
a) The set of alarm-triggering input patterns is linearly separable
b) The alarm behavior can be implemented using a single threshold unit
c) Exactly half of all possible input combinations result in an alarm
d) Increasing the threshold beyond the chosen value increases resistance to isolated sensor noise
e) The alarm output depends on the sequence in which sensor inputs arrive
Que5. If the threshold were incorrectly set to π = 2, which outcome would most likely occur?
a) The alarm would never activate
b) The alarm would activate only when all sensors are active
c) The alarm would activate more frequently, increasing false positives
d) The alarm behavior would become undefined
Que6. The anchor-pattern mapping in the table corresponds to which logical behavior of (π₯1, π₯2) (treating 1 as βhighβ and 0 as βlowβ)?
a) AND
b) OR
c) XOR
d) XNOR
Que7. Can a single linear-threshold classifier of the form π€1π₯1 + π€2π₯2 + π β₯ 0 correctly classify all four anchor patterns shown?
a) Yes, always
b) Yes, but only if b = 0
c) No
d) Yes, but only if π€1 = π€2
Que8. Suppose the team insists on using a single linear-threshold model and chooses parameters π€1 = 1, π€2 = 1 and π = β1. Which anchor groups will be predicted as Ε· = 1?
a) Only G4
b) G2 and G3
c) Only G2
d) G2, G3, and G4
Que9. Fill in the blank.
For the model in the previous question (π€1 = 1, π€2 = 1 and π = β1), how many of the four anchor patterns are classified correctly? __________
Que10. A two-unit deterministic system is proposed:
Unit U1 outputs 1 if π₯1 + π₯2 β₯ 1,
Unit U2 outputs 1 if π₯1 + π₯2 β₯ 2.
Final output is π¦ = 1 if U1 = 1 and U2 = 0, else π¦ = 0.
Which anchor inputs will this system classify as π¦ = 1?
Select all that apply.
a) (0,0)
b) (0,1)
c) (1,0)
d) (1,1)
Que11. Which logical condition best describes the accept decision specified in the policy?
a) π₯3 β§ (π₯1 β¨ π₯2 β¨ π₯4)
b) (π₯1 β§ π₯2) β¨ (π₯3 β§ π₯4)
c) π₯3 β (π₯1 β¨ π₯2 β¨ π₯4)
d) (π₯1 β¨ π₯2 β¨ π₯3 β¨ π₯4)
Que12. Why does a single linear-threshold rule fail to implement the specified policy for all inputs?
a) The input dimension is too high
b) The policy induces non-linearly separable input patterns
c) The features are binary
d) The bias term is missing
Que13. Which of the following input patterns must result in π¦ = 1 under the policy?
Select all that apply.
(Inputs listed as (π₯1, π₯2, π₯3, π₯4))
a) (0,0,1,1)
b) (1,0,1,0)
c) (0,0,0,1)
d) (0,1,0,0)
e) (0,0,1,0)
Que14. How many distinct input combinations produce π¦ = 1 under the stated policy?
a) 3
b) 5
c) 7
d) 9
Que15. Which of the following statements about the hierarchical design are correct?
Select all that apply.
a) It decomposes the decision into linearly separable subproblems
b) It can be collapsed into a single equivalent linear-threshold rule
c) It correctly implements the specified policy
d) It increases representational capacity compared to a single stage
e) It requires continuous-valued features
Deep Learning IIT Ropar Week 1 Nptel Assignment Answers (July-Dec 2025)
Que.1 For an MP neuron with input size 3 and threshold condition f(x) = 1 if xβ + xβ + xβ > 1
Which of the following input-output pairs are correct?
A) x = (1, 0, 0), y = 0
B) x = (0, 1, 1), y = 1
C) x = (0, 0, 0), y = 0
D) x = (1, 1, 0), y = 1
E) x = (1, 1, 1), y = 0
Que.2 What is the minimum number of input values that must be 1 for the MP neuron to output 1?
(Fill in the blank)
Que.3 Which of the following sensor combinations would trigger the alert?
A) x = (1, 1, 0)
B) x = (0, 1, 1)
C) x = (1, 1, 1)
D) x = (1, 0, 0)
E) x = (0, 0, 1)
Que.4 For McCulloch-Pitts (MP) neuron model, which of the below thresholding functions describes the above scenario?
A) f(x) = {1 if xβ+xβ+xβ > 2, 0 otherwise}
B) f(x) = {1 if xβ+xβ+xβ β₯ 2, 0 otherwise}
C) f(x) = {1 if xβ+xβ+xβ > 1, 0 otherwise}
D) None of the above
Que.5 Which change will help the model fire (output 1) when at least two inputs are 1?
A) Change the threshold from 2 to 1
B) Change the condition from β> 2β to ββ₯ 2β
C) Use weights instead of plain sums
D) Set threshold to 3
E) Make all inputs always 1
Que.6 Which of the following threshold values will ensure that the neuron functions as a strict majority gate (for 7 inputs)?
A) 3
B) 4
C) 5
D) 6
Que.7 For how many input combinations does it output 1? (MP neuron, 4 binary inputs, threshold: xβ+xβ+xβ β₯ 1)
A) 8
B) 15
C) 1
D) 0
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Que.8 A security system has 4 sensors. An MP neuron triggers an alarm when at least 3 sensors are active.
How many unique input cases will lead to an alarm?
(Fill in the blank)
Que.9 An MP neuron with 4 binary inputs gives output 1 for 11 different input combinations. What is the likely threshold ΞΈ?
A) 2
B) 3
C) 1
D) 4
Que.10 You’re building a neural circuit using a perceptron to identify when both security switches are ON.
Which Boolean function would you implement?
A) OR
B) XOR
C) AND
D) XNOR
Que.11 You want the gate to output 1 only when exactly one input is 1.
Which function and can a single perceptron implement it?
A) AND, Yes
B) XOR, No
C) OR, Yes
D) NOR, Yes
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Que.12 Gate opens only if exactly one user presses the button.
Which logic function and can it be modeled by a perceptron?
A) XOR, Yes
B) XOR, No
C) AND, Yes
D) NOR, No
Que.13 Why use the perceptron algorithm in tumor classification (malignant/benign)?
A) To group tumors into clusters
B) To classify tumors
C) To compute the shortest path
D) To solve optimization
Que.14 The weight vector w and decision boundary are observed to make an angle. What’s the relation?
A) Weight vector is parallel
B) Weight vector lies on the boundary
C) Weight vector is perpendicular
D) Weight vector changes direction randomly
Que.15 If initialized to w = [0.0, 0.0], will the perceptron converge?
A) Never converges
B) Converges after some iterations
C) Error remains non-zero
D) Error becomes zero eventually
Que.16 If initialized randomly in range [-0.5, 0.5], which is true?
A) May fail to converge
B) Will always converge
C) Time may vary
D) Helps escape local minima
Que.17 Given perceptron: w = [1,1], b = -1, y = 1 if wΒ·x + b > 0. Which inputs are correctly classified?
A) (1,1,1)
B) (0,0,1)
C) (1,0,0)
D) (0,1,0)
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Que.18 Which threshold activates MP neuron only when all 7 inputs are ON?
A) 5
B) 6
C) 7
D) 8
Que.19 In 7-voter system, at least 5 YES required. What threshold value for MP neuron?
(Fill in the blank)
Que.20 If w = [-1, -1] and y = 1, what must be true for x = (a, b)?
A) a + b < 0
B) a + b = 0
C) a + b > 0
D) ab > 0
Que.21 Which of the following points lie on decision boundary for w = [-1, -1]?
A) (2, 2)
B) (1, -1)
C) (3, -3)
D) (0.5, 0.5)
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Que.22 Given w = [2, 3, -1], b = -2, input = [1, 0, -1]. Output = ?
(Fill in the blank)
Que.23 How many updates will perceptron (w = [3, 3]) perform in one pass over the dataset?
(Fill in the blank)
Que.24 Final weight vector after convergence (w = [0, 0])?
A) (1, 0)
B) (-1, -1)
C) (0, 1)
D) (1, 1)
Que.25 What is the final weight vector after convergence?
A) (1, 2)
B) (-2, -1)
C) (-1, -1)
D) None of these
Que.26 Why does adding bias in perceptron help?
A) Shifts boundary away from origin
B) Rotates decision boundary
C) Increases epochs
D) None of the above
Que.27 For perceptron convergence guarantee, which condition must be true?
A) Data must be linearly separable
B) Weights must be non-zero
C) Finite data points
D) Must include bias
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Que.28 What does “absolutely linearly separable” mean?
A) There exists a hyperplane classifying all points correctly
B) Points lie on same coordinate axis
C) Equal number of points in each set
D) Points in P closer to origin than N
Deep Learning IIT Ropar Week 1 Nptel Assignment Answers (Jan-Apr 2025)
Course Link: Click Here
Que. 1) The points GGG and CCC will be classified as?
a) (C, 0), (G, 0)
b) (C, 0), (G, 1)
c) (C, 1), (G, 1)
d) (C, 1), (G, 0)
Que. 2) The statement that βthere exists more than one decision line that could separate these data points with zero errorβ is:
a) True
b) False
Que. 3) Suppose that we multiply the weight vector www by β1-1β1. Then the same points GGG and CCC will be classified as?
a) (C, 0), (G, 0)
b) (C, 0), (G, 1)
c) (C, 1), (G, 1)
d) (C, 1), (G, 0)
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Que. 4) Which of the following can be achieved using the perceptron algorithm in machine learning?
a) Grouping similar data points into clusters, such as organizing customers based on purchasing behavior.
b) Solving optimization problems, such as finding the maximum profit in a business scenario.
c) Classifying data, such as determining whether an email is spam or not.
d) Finding the shortest path in a graph, such as determining the quickest route between two cities.
Que. 5) Assume that the elements in www are initialized to zero and the perceptron learning algorithm is used to update the weights www. If the learning algorithm runs for long enough iterations, then:
a) The algorithm never converges
b) The algorithm converges (i.e., no further weight updates) after some iterations
c) The classification error remains greater than zero
d) The classification error becomes zero eventually
Que. 6) We know that the decision boundary learned by the perceptron is a line in R2\mathbb{R}^2R2. Suppose the input vector xβR4x \in \mathbb{R}^4xβR4, then the perceptron decision boundary will divide the whole R4\mathbb{R}^4R4 space into how many regions?
a) It depends on whether the data points are linearly separable or not.
b) 3
c) 4
d) 2
e) 5
Que. 7) Choose the correct input-output pair for the given MP Neuron.f(x)={1if x1+x2+x3<20otherwisef(x) = \begin{cases} 1 & \text{if } x_1 + x_2 + x_3 < 2 \\ 0 & \text{otherwise} \end{cases} f(x)={10βif x1β+x2β+x3β<2otherwiseβ
- y=1y = 1y=1 for (x1,x2,x3)=(0,0,0)(x_1, x_2, x_3) = (0, 0, 0)(x1β,x2β,x3β)=(0,0,0)
- y=0y = 0y=0 for (x1,x2,x3)=(0,0,1)(x_1, x_2, x_3) = (0, 0, 1)(x1β,x2β,x3β)=(0,0,1)
- y=1y = 1y=1 for (x1,x2,x3)=(1,0,0)(x_1, x_2, x_3) = (1, 0, 0)(x1β,x2β,x3β)=(1,0,0)
- y=1y = 1y=1 for (x1,x2,x3)=(1,1,1)(x_1, x_2, x_3) = (1, 1, 1)(x1β,x2β,x3β)=(1,1,1)
- y=0y = 0y=0 for (x1,x2,x3)=(1,0,1)(x_1, x_2, x_3) = (1, 0, 1)(x1β,x2β,x3β)=(1,0,1)
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Que. 8) Suppose that the perceptron model is used to classify the data points. The weights www are initialized to w=[1,1]w = [1, 1]w=[1,1], and the rule y=1y = 1y=1 if wTx>0w^T x > 0wTx>0 (otherwise y=0y = 0y=0) is used for classification. How many times will the weight vector www get updated during the entire training process?
a) 0
b) 1
c) 2
d) Not possible to determine
Que. 9) Which of the following threshold values of MP neuron implements the AND Boolean function? Assume that the number of inputs to the neuron is 3, and the neuron does not have any inhibitory inputs.
a) 1
b) 2
c) 3
d) 4
e) 5
Que. 10) Consider points shown in the picture. The vector w=[β1,1]w = [-1, 1]w=[β1,1]. As per this weight vector, the perceptron algorithm will predict which classes for the data points x1x_1x1β and x2x_2x2β:
x1=β1x_1 = -1×1β=β1
x1=1x_1 = 1×1β=1
x2=β1x_2 = -1×2β=β1
x2=1x_2 = 1×2β=1
- y=1y = 1y=1 for x1x_1x1β
- y=0y = 0y=0 for x2x_2x2β
Deep Learning IIT Ropar Week 1 Nptel Assignment Answers (July-Dec 2024)
Course Link: Click Here
For answers or latest updates join our telegram channel: Click here to join
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Q1. Consider the following table, where x1 and x2 are features and y is a label
Assume that the elements in w are initialized to zero and the perception learning algorithm is used to update the weights w .If the learning algorithm runs for long enough iterations, then
The algorithm never converges
The algorithm converges (i.e., no further weight updates) after some iterations
The classification error remains greater than zero
The classification error becomes zero eventually
Q2. In the perceptron model, the weight w vector is perpendicular to the linear decision boundary at all times.
True
False
For answers or latest updates join our telegram channel: Click here to join
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Q3.What is the perceptron algorithm used for?
Clustering data points
Classifying data
Solving optimization problems
Finding the shortest path in a graph
Q4. Choose the correct input-output pair for the given MP Neuron. f(x)={1,0,if x1+x2+x3>2 0,otherwise
y=1 for (x1,x2,x3)=(0,1,1)
y=0 for (x1,x2,x3)=(0,0,1)
y=1 for (x1,x2,x3)=(0,0,0)
y=1 for (x1,x2,x3)=(1,1,1)
y=0 for (x1,x2,x3)=(1,0,1)
Answer: b)y=0 for (x1,x2,x3)=(0,0,1) , d,)y=1 for (x1,x2,x3)=(1,1,1) ,e) y=0 for (x1,x2,x3)=(1,0,1)
For answers or latest updates join our telegram channel: Click here to join
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Q5.Which of the following Boolean functions can be implemented using a perceptron?
NOR
NAND
NOT
XOR
Answer: NOR
NAND
NOT
Q6. Which of the following threshold values of MP neuron implements AND Boolean function? Assume that the number of inputs to the neuron is 7 and the neuron does not have any inhibitory inputs.
1
3
6
7
8
Answer: 7
For answers or latest updates join our telegram channel: Click here to join
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Q7.Suppose we have a boolean function that takes 4 inputs x1,x2,x3,x4? We have an MP neuron with parameter ΞΈ=3 . For how many inputs will this MP neuron give output y=1?
5
4
1
16
Answer: 5
Q8.Consider points shown in the picture. The vector w=[β1β1].As per this weight vector, the Perceptron algorithm will predict which classes for the data points x1 and x2.
x1=β1
x1=1
x2=β1
x2=1
Answer:a) x1=β1, d) x2=1
For answers or latest updates join our telegram channel: Click here to join
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Q9.Consider the following table, where x1 and x2 are features (packed into a single vector x=[x1x2]
) and y is a label:
Suppose that the perceptron model is used to classify the data points. Suppose further that the weights w
are initialized to w=[11] .The following rule is used for classification,
2
1
0
Not possible to determine
Answer: 0
Q10.Which Boolean function with two inputs x1 and x2 is represented by the following decision boundary? (Points on boundary or right of the decision boundary to be classified 1)
AND
OR
XOR
NAND
Answer: OR
Q11.Choose the correct input-output pair for the given MP Neuron.
y={1,ifx1+x2+x3β₯2
0, otherwise
y=1 for (x1,x2,x3)=(0,1,1)
y=0 for (x1,x2,x3)=(0,0,1)
y=1 for (x1,x2,x3)=(1,1,1)
y=0 for (x1,x2,x3)=(1,0,0)
Answer: a),b),c)
Q12.Suppose we have a boolean function that takes 4 inputs x1, x2, x3, x4? We have an MP neuron with parameter ΞΈ=2 .For how many inputs will this MP neuron give output y=1?
11
21
15
8
Answer: 8
For answers or latest updates join our telegram channel: Click here to join
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Q13.We are given the following data:
Can you classify every label correctly by training a perceptron algorithm? (assume bias to be 0 while training)
Yes
No
Answer: No
Q14.We are given the following dataset with features as (x1,x2) and y as the label (-1,1). If we apply the perception algorithm on the following dataset with w initialized as (0,0). What will be the value of w when the algorithm converges? (Start the algorithm from (2,2)
(-2,2)
(2,1)
(2,-1)
None of These
Answer: (2,-1)
For answers or latest updates join our telegram channel: Click here to join
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Q15.Consider points shown in the picture. The vector w is (-1,0). As per this weight vector, the Perceptron algorithm will predict which classes for the data points x1 and x2.
x1=1
x2=1
x1=-1
x2=-1
Answer: x2=1 ,x1=-1
Q16.Given an MP neuron with the inputs as x1,x2,x3,x4,x5 and threshold ΞΈ=3 where x5 is inhibitory input. For input (1,1,1,0,1) what will be the value of y?
y=0
y=1 since ΞΈβ₯3
y=1/2
Insufficient information
Answer: y=0
For answers or latest updates join our telegram channel: Click here to join
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Q17.An MP neuron takes two inputs x1 and x2. Its threshold is ΞΈ=0 .Select all the boolean functions this MP neuron may represent.
AND
NOT
OR
NOR
Answer: NOR
For answers or latest updates join our telegram channel: Click here to join
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Q18. What is the output of a perceptron with weight vector w=[2β31] and bias b=β2
when the input is x=[10β1] ?
0
1
-1
2
Answer: -1
For answers or latest updates join our telegram channel: Click here to join
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
Q19 .What is the βwinter of AIβ referring to in the history of artificial intelligence?
The period during winter when AI technologies are least effective due to cold temperatures
A phase marked by decreased funding and interest in AI research.
The season when AI algorithms perform at their peak efficiency.
A period characterized by rapid advancements and breakthroughs in AI technologies.
Answer: A phase marked by decreased funding and interest in AI research.
For answers or latest updates join our telegram channel: Click here to join
These are Deep Learning IIT Ropar Week 1 Nptel Assignment Answers
More Weeks of Deep Learning – IIT Ropar : Click here
More Nptel Courses: https://progiez.com/nptel-assignment-answers
