We Discuss About That NPTEL Deep Learning IIT Ropar Assignment 4 Answers 2022

NPTEL Deep Learning IIT Ropar Assignment 4 Answers 2022 – Here All The Questions and Answers Provided to Help All The Students and NPTEL Candidate as a Reference Purpose, It is Mandetory to Submit Your Weekly Assignment By Your Own Understand Level.

Are you looking for the Assignment Answers to **NPTEL Deep Learning IIT Ropar Assignment 4 Answers 2022? **If Yes You are in Our Great Place to Getting Your Solution, This Post Should be help you with the Assignment answer to the **Nation**** al Programme on Technology Enhanced Learning (NPTEL)** Course

**“NPTEL Deep Learning IIT Ropar Assignment 4 Answers 2022”**

**NPTEL Deep Learning IIT Ropar Assignment**

**ABOUT THE COURSE :**

**Next Week Assignment Answers**

This course can have Associate in Nursing unproctored programming communication conjointly excluding the Proctored communication, please check announcement section for date and time. The programming communication can have a weightage of twenty fifth towards the ultimate score.

- Assignment score = 25% of average of best 8 assignments out of the total 12 assignments given in the course.
**( All assignments in a particular week will be counted towards final scoring – quizzes and programming assignments).**- Unproctored programming exam score = 25% of the average scores obtained as part of Unproctored programming exam – out of 100
- Proctored Exam score =50% of the proctored certification exam score out of 100

**YOU WILL BE ELIGIBLE FOR A CERTIFICATE ONLY IF ASSIGNMENT SCORE >=10/25 AND**

**UNPROCTORED PROGRAMMING EXAM SCORE >=10/25 AND PROCTORED EXAM SCORE >= 20/50.**

**If any one of the 3 criteria is not met, you will not be eligible for the certificate even if the Final score >= 40/100.**

**CHECK HERE OTHERS NPTEL ASSIGNMENTS ANSWERS **

*BELOW YOU CAN GET YOUR ***NPTEL Deep Learning IIT Ropar Assignment 4 Answers 2022****?** :

**NPTEL Deep Learning IIT Ropar Assignment 4 Answers 2022**

**?**:

1. Consider the movement on the 3D error surface for Vannila Gradient Descent Algorithm. Select all the options that are TRUE.

a. Smaller the gradient, slower the movement

b. Larger the gradient, faster the movement

c. Gentle the slope, smaller the gradient

d. Steeper the slope, smaller the gradient

Answer:-

2. Pick out the drawback in Vannila gradient descent algorithm.

a. Very slow movement on gentle slopes

b. Increased oscillations before converging

c. escapes minima because of long strides

d. Very slow movement on steep slopes

Answer:-

NPTEL Deep Learning – IIT Ropar Assignment 4 Answers 2022

3. Comment on the update at the tth update in the Momentum-based Gradient Descent.

a. weighted average of gradient

b. Polynomial weighted average

c. Exponential weighted average of gradient

d. Average of recent three gradients

Answer:-

4. Given a horizontal slice of the error surface as shown in the figure below, if the error at the position p is 0.49 then what is the error at point q?

a. 0.70

b. 0.69

c. 0.49

d. 0

Answer:-

5. Identify the update rule for Nesterov Accelerated Gradient Descent.

Answer:-

6. Select all the options that are TRUE for Line search.

a. w is updated using different learning rates

b. updated value of w always gives the minimum loss

c. Involves minimum calculation

d. Best value of Learning rate is used at every step

Answer:-

NPTEL Deep Learning – IIT Ropar Assignment 4 Answers 2022

7. Assume you have 1,50,000 data points, Mini batch size being 25,000, one epoch implies one pass over the data, and one step means one update of the parameters, What is the number of steps in one epoch for Mini-Batch Gradient Descent?

a. 1

b. 1,50,000

c. 6

d. 60

Answer:-

8. Which of the following learning rate methods need to tune two hyperparameters?

I. step decay

II. exponential decay

III. 1/t decay

a. I and II

b. II and III

c. I and III

d. I, II and III

Answer:-

9. How can you reduce the oscillations and improve the stochastic estimates of the gradient that is estimated from one data point at a time?

a. Mini-Batch

b. Adam

c. RMSprop

d. Adagrad

Answer:-

10. Select all the statements that are TRUE.

a. RMSprop is very aggressive when decaying the learning rate

b. Adagrad decays the learning rate in proportion to the update history

c. In Adagrad, frequent parameters will receive very large updates because of the decayed learning rate

d. RMSprop has overcome the problem of Adagrad getting stuck when close to convergence

Answer:-

Yhaa You have done it but next? if YOU Want to your OthersNPTEL Deep Learning IIT Ropar Assignment 4 Answers 2022