Anh Viet Doan BDS Sep 21 S4 SYD Machine Learning ETE

BDS Sep 21 S4 SYD Machine Learning ETE
Anh Viet Doan | 26 Apr 2023
Mercer-Mettl | Anh Viet Doan Page 1 / 18

Test Name::
BDS Sep 21 S4 SYD Machine Learning ETE
Overall Status: Completed Detailed Status: Test-taker Completed Test Finish Time: April 26, 2023 01:46:41 PM AEST
Anh Viet Doan

AV
anh.bs21don043@spjain.org
Last Name: Doan
Date of birth: Feb 3, 2003
Contact No: 0452189276
SP Jain student ID/Campus ID: BS21DON043
Country: Vietnam
Test-Taker ID: - 96938363

Question-Wise Details
Section 1 15 24m 50s 36/45

Section #1 question(s) Time taken Marks Scored
Q.
Question 1 Time taken: 58s Marks Scored: 3/3
1
Which of the following is a supervised algorithm?
Response:
OPTIONS RESPONSE ANSWER
Logistic regression
K-means
DBSCAN
Both B & C.
Q.
2
PCA stands for
Response:
Principal Categorical Analysis
Principal Component Analysis
Practical Categorical Analysis
Practical Component Analysis

Q.
3
PCA is used for dimensionality reduction
Is the above statement True or False?
Response:
True
False
Can’t say based on information provided.
Q.
Question 4 Time taken: 4m 15s Marks Scored: 3/3
4
In XGBoost for regression, the output value is given by:
Response:

Q.
5
In XGBoost for regression, the loss function is:
Response:
There is no loss function, XGBoost uses gradient boosting.
XGBoost minimizes Huber loss
None of the above.
Q.
6
Which of the following are Decision trees?
Response:
CART
ID3
Both A and B
None of the above

Q.
7
Cost function in machine learning is generally
Response:
Minimized
Maximized
Multiplied
None of the above
Q.
8
Which of the following regularisation types also help in reducing dimensionality?
Response:
L1 regularisation
L2 regularisation
Pruning
Feature Engineering
All of the above.

Q.
9
Which of the following models is best suited if you only continuous features?
Response:
Multinomial Naïve Bayes
Gaussian Naïve Bayes
Categorical Naïve Bayes
None of the above
Any of A,B,C can be used
Cannot say based on given information
Q.
10
In ensemble learning, several weak models are combined to create a strong model.
Is this statement true or false?
Response:
True
False

Q.
11
Mini - Batch Gradient descent uses
Response:
Batch containing a subset of all samples
All samples
One sample picked randomly.
One sample picked from a mini-batch of samples
None of the above
Q.
12
linear models are more prone to:
Response:
Underfitting
Overfitting
Both Overfitting and Underfitting
None of the above

Q.
13
Regularization is used to reduce overfitting.
Is the above statement True or False?
Response:
True
False
Q.
14
Which of the following are types of Machine Learning?
Response:
Supervised Learning
Unsupervised Learning
Reinforcement Learning
All of the above

Q.
15
In a binary classification problem, a function that measures impurity in a decision tree should maximize when
Response:
+ class is 50% and -ve class is 50%

Section 2 8 24m 42s 40/40

Q.
1
Will the code shown below work?
Response:
Yes, it will work
No, it won’t because of syntax errors
No, it won’t because there is no call to the fit() function
None of the above
Q.
2
How many decision trees will be built by the following code?
Response:
300/100
300
300*10

Q.
3
Suppose you have 2 features (Cash and Debt).
Using PCA, you have found the Principal Component 1 (PC1) shown in blue below:
If the slope of PC1 is 1/ 4, then find the un-normalized length of the red vector that stretches from (0,0) to (4,1).
Response:
0.2
4.12

Q.
4
Suppose you have 2 features (Cash and Debt).
Using PCA, you have found the Principal Component 1 (PC1) shown in blue below:
If the slope of PC1 is 1/ 4, the find the loading scores of PC1.
Response:
0.97 and 0.242
0.235 and 0.856
0.722 and 0.333
1 and 5

Q.
5
If for 3 data points the distance between their projections onto principal component 1 (PC1) and origin is 1,2 and 3 then the eigenvalue of PC1
is:
Response:
15
14
13
12

Q.
6
Based on the following code, answer the question below:
If the output of the code is:
Then the least important feature for predicting class in the iris data set is
Response:
Sepal length
Sepal width
Petal length
Petal width

Q.
7
Suppose you are using XGBoost for regression and you have the following residuals in the root node
If λ=1, What is the similarity score for this root node?
Response:
0.35
0.3
0.20
0.25
Q.
8
How many rounds of training will happen in the following code:
Response:
30
50
25

Section 3 1 51m 50s 0/15

Q.
1
Section C : Coding Questions ( 15 Marks)
Write your code in the Jupyter notebook named “Section C - Machine learning April 2023 Final 1.ipynb”
Save the notebook as <Your_name>.ipynb
Upload the notebook to submission point as instructed.
End of Examination
Response:
Anh Viet Doan.ipynb

31.04 KB Click to Download
File Upload Settings for this question:
File Types Allowed All File Types Allowed by Mettl
Max marks: 15
EVALUATOR’S NAME MARKS EVALUATION COMMENTS LAST MODIFIED ON
Aditya Narvekar 0.0 File from mid-term has been 06:36 PM Apr 27, 2023
uploaded.

About the Report
This Report is generated electronically on the basis of the inputs received from the assessment takers. This Report including the AI flags that are generated in
case of availing of proctoring services, should not be solely used/relied on for making any business, selection, entrance, or employment-related decisions. Mettl
accepts no liability from the use of or any action taken or refrained from or for any and all business decisions taken as a result of or reliance upon anything,
including, without limitation, information, advice, or AI flags contained in this Report or sources of information used or referred to in this Report.

Anh Viet Doan BDS Sep 21 S4 SYD Machine Learning ETE

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Anh Viet Doan BDS Sep 21 S4 SYD Machine Learning ETE

Uploaded by

Copyright:

Available Formats

BDS Sep 21 S4 SYD Machine Learning ETE

Anh Viet Doan | 26 Apr 2023

Mercer-Mettl | Anh Viet Doan Page 1 / 18

BDS Sep 21 S4 SYD Machine Learning ETE

Anh Viet Doan

Last Name: Doan

Date of birth: Feb 3, 2003

Contact No: 0452189276

SP Jain student ID/Campus ID: BS21DON043

Mercer-Mettl | Anh Viet Doan Page 2 / 18

Section 1 15 24m 50s 36/45

Which of the following is a supervised algorithm?

OPTIONS RESPONSE ANSWER

PCA stands for

OPTIONS RESPONSE ANSWER

Principal Categorical Analysis

Principal Component Analysis

Practical Categorical Analysis

Practical Component Analysis

Mercer-Mettl | Anh Viet Doan Page 3 / 18

PCA is used for dimensionality reduction

Is the above statement True or False?

OPTIONS RESPONSE ANSWER

Can’t say based on information provided.

In XGBoost for regression, the output value is given by:

OPTIONS RESPONSE ANSWER

Mercer-Mettl | Anh Viet Doan Page 4 / 18

In XGBoost for regression, the loss function is:

OPTIONS RESPONSE ANSWER

There is no loss function, XGBoost uses gradient boosting.

XGBoost minimizes Huber loss

None of the above.

Which of the following are Decision trees?

OPTIONS RESPONSE ANSWER

None of the above

Mercer-Mettl | Anh Viet Doan Page 5 / 18

Cost function in machine learning is generally

OPTIONS RESPONSE ANSWER

None of the above

Which of the following regularisation types also help in reducing dimensionality?

OPTIONS RESPONSE ANSWER

All of the above.

Mercer-Mettl | Anh Viet Doan Page 6 / 18

OPTIONS RESPONSE ANSWER

Multinomial Naïve Bayes

Gaussian Naïve Bayes

Categorical Naïve Bayes

None of the above

Any of A,B,C can be used

Cannot say based on given information

Is this statement true or false?

OPTIONS RESPONSE ANSWER

Mercer-Mettl | Anh Viet Doan Page 7 / 18

Mini - Batch Gradient descent uses

OPTIONS RESPONSE ANSWER

Batch containing a subset of all samples

One sample picked randomly.

One sample picked from a mini-batch of samples

None of the above

linear models are more prone to:

OPTIONS RESPONSE ANSWER

Both Overfitting and Underfitting

None of the above