Scribd
Upload
75 views

NPTEL Live Session Week 1 Deep Learning-IIT Ropar

Uploaded by

AARTI NAGPAL
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
75 views

NPTEL Live Session Week 1 Deep Learning-IIT Ropar

Uploaded by

AARTI NAGPAL
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 26

NPTEL Live Session

Week 1
Deep Learning-IIT Ropar
Ayan Maity
PhD Scholar,
CSE,IIT Kharagpur

29/07/24
Question 1
Which of the following is/are applications of deep learning?

a. Image Recognition
b. Text Sentiment Analysis
c. Image Captioning
d. All of the above
Question 1
Which of the following is/are applications of deep learning?

a. Image Recognition
b. Text Sentiment Analysis
c. Image Captioning
d. All of the above

Answer: d. All of the above


Question 2
Which of the following logical functions is not linearly separable?

a. AND
b. OR
c. XOR
d. None of the above
Question 2
Which of the following logical functions is not linearly separable?

a. AND
b. OR
c. XOR
d. None of the above

Answer: c. XOR
Question 3
Which of the following points are TRUE for McCulloch-Pitts (MP) Neuron Model and Perceptron Model?

i. Inputs are not weighted in MP neurons

ii. Perceptron model can take weights with respective to inputs provided.

iii. MP neuron model process real number inputs as well

iv. Perceptron model process real number inputs as well

a. i, ii
b. i, ii, iii
c. i, ii, iv
d. i, ii, iii, iv
Question 3
Which of the following points are TRUE for McCulloch Pitts (MP) Neuron Model and Perceptron Model?

i. Inputs are not weighted in MP neurons

ii. Perceptron model can take weights with respective to inputs provided.

iii. MP neuron model process real inputs as well

iv. Perceptron model process real inputs as well

a. i, ii
b. i, ii, iii
c. i, ii, iv
d. i, ii, iii, iv

Answer: c. i, ii ,iv
Question 4
Which of the following statements is true for the Perceptron Learning Algorithm?

Statement I: Threshold needs to be hand coded

Statement Il: Threshold can be learnt

a. I
b. II
c. None of the statements
Question 4
Which of the following statements is true for the Perceptron Learning Algorithm?
Statement I: Threshold needs to be hand coded
Statement Il: Threshold can be learnt
a. I
b. II
c. None of the statements
Answer: b. II
Question 5
Consider the following McCulloch Pitts unit in the figure. Identify the Boolean
function for which the neuron fires only if the threshold 𝚹=3?

a. AND
b. OR
c. NOR
d. XOR
Question 5
Consider the following McCulloch Pitts unit in the figure. Identify the Boolean
function for which the neuron fires only if the threshold 𝚹=3?

a. AND
b. OR
c. NOR
d. XOR

Answer: a. AND
Question 6
The perceptron given below takes two binary valued inputs {0,1}. Which of the following logical functions does it
compute?

a. AND
b. OR
c. NAND
d. None of these
Question 6
The perceptron given below takes two binary valued inputs {0,1}. Which of the following logical functions does it
compute?

a. AND
b. OR
c. NAND
d. None of these

Answer : b. OR
Question 7
Suppose we have a boolean function with 5 inputs x1, x2, x3, x4, x5. We have an McCulloch-Pitts
(MP) neuron with parameter 𝚹=1. For how many inputs will this MP neuron give output y=1?

a. 21
b. 31
c. 30
d. 32
Question 7
Suppose we have a boolean function with 5 inputs x1, x2, x3, x4, x5. We have an McCulloch-Pitts
(MP) neuron with parameter 𝚹=1. For how many inputs will this MP neuron give output y=1?

a. 21
b. 31
c. 30
d. 32

Answer: b. 31
Question 8

Consider the data given below.

Is it possible to classify every data point correctly


using a perceptron algorithm?

a. Yes
b. No
c. Can not be determined
Question 8

Consider the data given below.

Is it possible to classify every data point correctly


using a perceptron algorithm?

a. Yes
b. No
c. Can not be determined

Answer: a. Yes
Question 9

Consider the data given below.

Is it possible to classify every data point correctly


using a perceptron algorithm?

a. Yes
b. No
c. Can not be determined
Question 9

Consider the data given below.

Is it possible to classify every data point correctly


using a perceptron algorithm?

a. Yes
b. No
c. Can not be determined

Answer: b. No
Question 10

What is the output of a perceptron with weight vector w = [ 1, 5 , -2] and bias b = -1, when the input
is x = [2, 1, 2]?

a. 1
b. 0
c. -1
d. None of the above
Question 10

What is the output of a perceptron with weight vector w = [ 1, 5 , -2] and bias b = -1, when the input
is x = [2, 1, 2]?

a. 1
b. 0
c. -1
d. None of the above

Answer: a. 1
Question 11

Which type of neural networks is best suited for sequential data (e.g. time series
data, text data, audio data etc.)?

a. Convolutional Neural Networks


a. Multi-Layer Perceptron
b. Recurrent Neural Networks
Question 11

Which type of neural networks is best suited for sequential data (e.g. time series
data, text data, audio data etc.)?

a. Convolutional Neural Networks


b. Multi-Layer Perceptron
c. Recurrent Neural Networks

Answer: c. Recurrent Neural Networks


Question 12

Which type of neural networks is best suited for image recognition tasks?

a. Convolutional Neural Networks


a. Multi-Layer Perceptron
b. Recurrent Neural Networks
Question 12

Which type of neural networks is best suited for image recognition tasks?

a. Convolutional Neural Networks


a. Multi-Layer Perceptron
b. Recurrent Neural Networks

Answer: a. Convolutional Neural Networks


THE END

You might also like