# NPTEL Deep Learning – IIT Ropar Assignment 7 Answers 2022

NPTEL Deep Learning – IIT Ropar Assignment 7 Answers 2022:- In this post, We have provided answers of Deep Learning – IIT Ropar Assignment 4. We provided answers here only for reference. Plz, do your assignment at your own knowledge.

## About Deep Learning IIT – Ropar

Deep Learning has received a lot of attention over the past few years and has been employed successfully by companies like Google, Microsoft, IBM, Facebook, Twitter etc. to solve a wide range of problems in Computer Vision and Natural Language Processing. In this course, we will learn about the building blocks used in these Deep Learning based solutions. Specifically,

we will learn about feedforward neural networks, convolutional neural networks, recurrent neural networks and attention mechanisms. We will also look at various optimization algorithms such as Gradient Descent, Nesterov Accelerated Gradient Descent, Adam, AdaGrad and RMSProp which are used for training such deep neural networks. At the end of this course, students would have knowledge of deep architectures used for solving various Vision and NLP tasks

CRITERIA TO GET A CERTIFICATE

Average assignment score = 25% of average of best 8 assignments out of the total 12 assignments given in the course.
Exam score = 75% of the proctored certification exam score out of 100

Final score = Average assignment score + Exam score

YOU WILL BE ELIGIBLE FOR A CERTIFICATE ONLY IF AVERAGE ASSIGNMENT SCORE >=10/25 AND EXAM SCORE >= 30/75. If one of the 2 criteria is not met, you will not get the certificate even if the Final score >= 40/100.

## NPTEL Deep Learning – IIT Ropar Assignment 7 Answers 2022

1. Bias enables shifting the activation function by adding a constant to the input. How is it related to model complexity? Select all that apply.

a. Complex model has a low bias
b. Simple model has a low bias
c. Complex model has a high bias
d. Simple model has a high bias

`Answer:- `

2. What are the preferred values for Bias and Variance to yield a low Mean Squared Error?

a. Low bias and high variance
b. Low variance and high bias
c. Low bias and low variance
d. Optimal value for both bias and variance

`Answer:- `

3. Given the relation between Validation Error and Model complexity for a Deep Neural Network to classify dogs and cats, Which of the points correspond to underfitting?

a. a
b. b
c. c
d. both a and b

`Answer:- `

4. Consider the Deep Neural Network as described in Question 3, Which of the following instances marked on graph marks the preferred optimal complexity?

a. a
b. b
c. c
d. both a and b

`Answer:- `

5. Which of the following statements are True?

Statement I. Training a model to drive the training error to zero ensures high model performance.
Statement II. Tuning for Validation error ensures that the model does not overfit

a. Only I
b. Only II
c. Both I and II
d. None

`Answer:- `

6. Pick out the strategies to prevent overfitting.

a. Reduce the number of hidden layers
b. Decrease the number of samples
c. Switch off some of the neurons in the neural network
d. Increase the number of hidden layers

`Answer:- `

7. Which of the following is CORRECT for Bagging?

a. Combines predictions from different neural network models on same data
b. Used to reduce variance within the dataset
d. Ensemble on models trained on same classifier using different instances

`Answer:- `

8. Suppose there are 20 nodes in a Deep Neural network and we implement Dropout by removing few nodes to obtain a thinned network. What is total number of such thinned networks that can be formed?

a. 20
b. (2)^20
c. (20)^2
d. ((2)^2)^20

`Answer:- `

9. Identify the need for regularization. Select all that apply.

a. Deep Neural networks are complex
b. Involves non-linearities
c. High possibility of overfitting
d. Involves many Parameters

`Answer:- `

10. You are training a neural network model using Early stopping technique.Given that the patience parameter is 2, When will you stop training?

a. 3
b. 4
c. 5
d. 6

`Answer:- `