We have been given a dataset with n records in which we have input attribute as x and output attribute as y. Suppose we use a linear regression method to model this data. To test our linear regressor, we split the data in training set and test set randomly. What do you expect will happen with bias and variance as you increase the size oftraining data?

bias increases and variance increases

bias decreases and variance increases

bias decreases and variance decreases

bias increases and variance decreases

Suppose that we have N independent variables (X1,X2… Xn) and dependent variable is Y. Now Imagine that you are applying linear regression by fitting the best fit line using least square error on this data. You found that correlation coefficient for one of it’s variable(Say X1) with Y is -0.95.Which of the following is true for X1?

relation between the x1 and y is neutral

relation between the x1 and y is weak

relation between the x1 and y is strong

relation between the x1 and y is neutral

correlation can’t judge the relationship

Suppose you have fitted a complex regression model on a dataset. Now, you are using Ridge regression with tuning parameter lambda to reduce its complexity. Choose the option(s) below which describes relationship of bias andvariance with lambda.

in case of very large lambda; bias is high, variance ishigh

in case of very large lambda; bias is low, variance islow

in case of very large lambda; bias is low, variance ishigh

in case of very large lambda; bias is high, variance islow

in case of very large lambda; bias is high, variance ishigh

Reinforcement learning is particularly efficient when .

the environment is not completely deterministic

it\s impossible to have a precise error measure

what is the function of ‘Supervised Learning’?

classifications, predict time series, annotate strings

940 + Mcqs in Machine Learning in Artificial Intelligence Page 1 McqOptions

1.	In a real problem, you should check to see if the SVM is separable and th
A.	true
B.	false
Answer» C.

Discussion

2.	Linear SVMs have no hyperparameters that need to be set by cross-valid
A.	true
B.	false
Answer» C.

Discussion

3.	If I am using all features of my dataset and I achieve 100% accura
A.	underfitting
B.	nothing, the m
C.	overfitting
Answer» D.

Discussion

4.	Suppose you are using RBF kernel in SVM with high Gamma valu
A.	the model wo
B.	uthe model wo
C.	the model wou
D.	none of the ab
Answer» C. the model wou

Discussion

5.	Support vectors are the data points that lie closest to the decision
A.	true
B.	false
Answer» B. false

Discussion

6.	100 people are at party. Given data gives informa
A.	0.4
B.	0.2
C.	0.6
D.	0.45
Answer» C. 0.6

Discussion

7.	For the given weather data, what is the probabilit
A.	0.5
B.	0.26
C.	0.73
D.	0.6
Answer» E.

Discussion

8.	For the given weather data, Calculate probability
A.	0.4
B.	0.64
C.	0.29
D.	0.75
Answer» C. 0.29

Discussion

9.	Problem: Players will play if weather is sunny. Is t
A.	true
B.	false
Answer» B. false

Discussion

10.	100 people are at party. Given data gives information about how many wear pink or not, and if a man or not. Imagine a pink wearing guest leaves, what is the probability of being aman
A.	0.4
B.	0.2
C.	0.6
D.	0.45
Answer» C. 0.6

Discussion

11.	For the given weather data, what is theprobability that players will play if weather is sunny
A.	0.5
B.	0.26
C.	0.73
D.	0.6
Answer» E.

Discussion

12.	Linear SVMs have no hyperparameters that needto be set by cross-validation
A.	true
B.	false
Answer» C.

Discussion

13.	Suppose you are using a Linear SVM classifier with 2 class classification problem. Now you have been given the following data in which some points are circled red that are representing support vectors.If you remove the following any one red points from the data. Does the decisionboundary will change?
A.	yes
B.	no
Answer» B. no

Discussion

14.	If I am using all features of my dataset and I achieve 100% accuracy on my training set, but~70% on validation set, what should I look outfor?
A.	underfitting
B.	nothing, the model is perfect
C.	overfitting
Answer» D.

Discussion

15.	Gaussian Naïve Bayes Classifier is _ distribution
A.	continuous
B.	discrete
C.	binary
Answer» B. discrete

Discussion

16.	Which of the following is not supervisedlearning?
A.	pca
B.	decisiontree
C.	naivebayesian
D.	linerarregression
Answer» B. decisiontree

Discussion

17.	Support vectors are the data points that lieclosest to the decision surface.
A.	true
B.	false
Answer» B. false

Discussion

18.	We usually use feature normalization before using the Gaussian kernel in SVM. What is true about feature normalization? 1. We do feature normalization so that new feature will dominate other 2. Some times, feature normalization is not feasible in case of categorical variables3. Feature normalization always helps when we useGaussian kernel in SVM
A.	1
B.	1 and 2
C.	1 and 3
D.	2 and 3
Answer» C. 1 and 3

Discussion

19.	The minimum time complexity for training an SVM is O(n2). According to this fact, what sizesof datasets are not best suited for SVM’s?
A.	large datasets
B.	small datasets
C.	medium sized datasets
D.	size does not matter
Answer» B. small datasets

Discussion

20.	For the given weather data, Calculate probabilityof not playing
A.	0.4
B.	0.64
C.	0.36
D.	0.5
Answer» D. 0.5

Discussion

21.	Multinomial Naïve Bayes Classifier is _ distribution
A.	continuous
B.	discrete
C.	binary
Answer» C. binary

Discussion

22.	Problem: Players will play if weather is sunny. Isthis statement is correct?
A.	true
B.	false
Answer» B. false

Discussion

23.	We have been given a dataset with n records in which we have input attribute as x and output attribute as y. Suppose we use a linear regression method to model this data. To test our linear regressor, we split the data in training set and test set randomly. What do you expect will happen with bias and variance as you increase the size oftraining data?
A.	bias increases and variance increases
B.	bias decreases and variance increases
C.	bias decreases and variance decreases
D.	bias increases and variance decreases
Answer» E.

Discussion

24.	We have been given a dataset with n records in which we have input attribute as x and output attribute as y. Suppose we use a linear regression method to model this data. To test our linear regressor, we split the data in training set and test set randomly. Now we increase the training set size gradually. As the training set size increases, what do you expect will happen with the meantraining error?
A.	increase
B.	decrease
C.	remain constant
D.	can’t say
Answer» E.

Discussion

25.	Suppose that we have N independent variables (X1,X2… Xn) and dependent variable is Y. Now Imagine that you are applying linear regression by fitting the best fit line using least square error on this data. You found that correlation coefficient for one of it’s variable(Say X1) with Y is -0.95.Which of the following is true for X1?
A.	relation between the x1 and y is weak
B.	relation between the x1 and y is strong
C.	relation between the x1 and y is neutral
D.	correlation can’t judge the relationship
Answer» C. relation between the x1 and y is neutral

Discussion

26.	In the mathematical Equation of Linear Regression Y = β1 + β2X + ϵ, (β1, β2) refers to
A.	(x-intercept, slope)
B.	(slope, x- intercept)
C.	(y-intercept, slope)
D.	(slope, y- intercept)
Answer» D. (slope, y- intercept)

Discussion

27.	Which of the following method(s) does not haveclosed form solution for its coefficients?
A.	ridgeregression
B.	lasso
C.	both ridgeand lasso
D.	none of both
Answer» C. both ridgeand lasso

Discussion

28.	What is/are true about ridge regression?1. When lambda is 0, model works like linear regression model2. When lambda is 0, model doesn’t work like linear regression model3. When lambda goes to infinity, we get very, very small coefficients approaching 04. When lambda goes to infinity, we get very, very large coefficients approachinginfinity
A.	1 and 3
B.	1 and 4
C.	2 and 3
D.	2 and 4
Answer» B. 1 and 4

Discussion

29.	Suppose you have fitted a complex regression model on a dataset. Now, you are using Ridge regression with tuning parameter lambda to reduce its complexity. Choose the option(s) below which describes relationship of bias andvariance with lambda.
A.	in case of very large lambda; bias is low, variance islow
B.	in case of very large lambda; bias is low, variance ishigh
C.	in case of very large lambda; bias is high, variance islow
D.	in case of very large lambda; bias is high, variance ishigh
Answer» D. in case of very large lambda; bias is high, variance ishigh

Discussion

30.	Which of the following selects the best K high-scorefeatures.
A.	selectpercentile
B.	featurehasher
C.	selectkbest
D.	all above
Answer» D. all above

Discussion

31.	It's possible to specify if the scaling process must include both mean and standard deviation using theparameters .
A.	with_mean=tru e/false
B.	with_std=true/ false
C.	both a & b
D.	none of the mentioned
Answer» D. none of the mentioned

Discussion

32.	In many classification problems, the target dataset is made up of categorical labels which cannot immediately be processed by any algorithm. An encoding is needed and scikit-learn offers atleast valid options
A.	1
B.	2
C.	3
D.	4
Answer» C. 3

Discussion

33.	which can accept a NumPy RandomStategenerator or an integer seed.
A.	make_blobs
B.	random_state
C.	test_size
D.	training_size
Answer» C. test_size

Discussion

34.	if there is only a discrete number of possible outcomes (called categories),the process becomes a .
A.	regression
B.	classification.
C.	modelfree
D.	categories
Answer» C. modelfree

Discussion

35.	During the last few years, many algorithms have been applied to deepneural networks to learn the best policy for playing Atari video games and to teach an agent how to associate the right action with an input representingthe state.
A.	logical
B.	classical
C.	classification
D.	none of above
Answer» E.

Discussion

36.	Reinforcement learning is particularly efficient when .
A.	the environment is not completely deterministic
B.	it\s often very dynamic
C.	it\s impossible to have a precise error measure
D.	all above
Answer» E.

Discussion

37.	what is the function of ‘Supervised Learning’?
A.	classifications, predict time series, annotate strings
B.	speech recognition, regression
C.	both a & b
D.	none of above
Answer» D. none of above

Discussion

38.	showed better performance than other approaches, even without a context-based model
A.	machine learning
B.	deep learning
C.	reinforcement learning
D.	supervised learning
Answer» C. reinforcement learning

Discussion

39.	there's a growing interest in pattern recognition and associative memories whose structure and functioningare similar to what happens in the neocortex. Such an
A.	regression
B.	accuracy
C.	modelfree
D.	scalable
Answer» D. scalable

Discussion

40.	Techniques involve the usage of both labeled and unlabeled data is called .
A.	supervised
B.	semi- supervised
C.	unsupervised
D.	none of the above
Answer» C. unsupervised

Discussion

41.	When it is necessary to allow the model to develop a generalization ability and avoid a common problemcalled .
A.	overfitting
B.	overlearning
C.	classification
D.	regression
Answer» B. overlearning

Discussion

42.	In the last decade, many researchers started trainingbigger and bigger models, built with several different layers that's why this approach is called .
A.	deep learning
B.	machine learning
C.	reinforcement learning
D.	unsupervised learning
Answer» B. machine learning

Discussion

43.	In reinforcement learning, this feedback is usually called as .
A.	overfitting
B.	overlearning
C.	reward
D.	none of above
Answer» D. none of above

Discussion

44.	can be adopted when it's necessary to categorize a large amount of data with a fewcomplete examples or when there's the need to
A.	supervised
B.	semi- supervised
C.	reinforcement
D.	clusters
Answer» C. reinforcement

Discussion

45.	Linear SVMs have no hyperparameters
A.	true
B.	false
Answer» C.

Discussion

46.	100 people are at party. Given data gives information about how many wear pink or not, and if a man or not. Imagine a pink wearing guest leaves, what is the probability of being a man
A.	0.4
B.	0.2
C.	0.6
D.	0.45
Answer» C. 0.6

Discussion

47.	For the given weather data, what is the probability that players will play if weather is sunny
A.	0.5
B.	0.26
C.	0.73
D.	0.6
Answer» E.

Discussion

48.	Linear SVMs have no hyperparameters that need to be set by cross-validation
A.	true
B.	false
Answer» C.

Discussion

49.	Suppose you are using a Linear SVM classifier with 2 class classification problem. Now you have been given the following data in which some points are circled red that are representing support vectors.If you remove the following any one red points from the data. Does the decision boundary will change?
A.	yes
B.	no
Answer» B. no

Discussion

50.	If I am using all features of my dataset and I achieve 100% accuracy on my training set, but ~70% on validation set, what should I look out for?
A.	underfitting
B.	nothing, the model is perfect
C.	overfitting
Answer» D.

Discussion

Explore topic-wise MCQs in Artificial Intelligence.

In a real problem, you should check to see if the SVM is separable and th

Linear SVMs have no hyperparameters that need to be set by cross-valid

If I am using all features of my dataset and I achieve 100% accura

Suppose you are using RBF kernel in SVM with high Gamma valu

Support vectors are the data points that lie closest to the decision

100 people are at party. Given data gives informa

For the given weather data, what is the probabilit

For the given weather data, Calculate probability

Problem: Players will play if weather is sunny. Is t

100 people are at party. Given data gives information about how many wear pink or not, and if a man or not. Imagine a pink wearing guest leaves, what is the probability of being aman

For the given weather data, what is theprobability that players will play if weather is sunny

Linear SVMs have no hyperparameters that needto be set by cross-validation

If I am using all features of my dataset and I achieve 100% accuracy on my training set, but~70% on validation set, what should I look outfor?

Gaussian Naïve Bayes Classifier is _ distribution

Which of the following is not supervisedlearning?

Support vectors are the data points that lieclosest to the decision surface.

The minimum time complexity for training an SVM is O(n2). According to this fact, what sizesof datasets are not best suited for SVM’s?

For the given weather data, Calculate probabilityof not playing

Multinomial Naïve Bayes Classifier is _ distribution

Problem: Players will play if weather is sunny. Isthis statement is correct?

In the mathematical Equation of Linear Regression Y = β1 + β2X + ϵ, (β1, β2) refers to

Which of the following method(s) does not haveclosed form solution for its coefficients?

Suppose you have fitted a complex regression model on a dataset. Now, you are using Ridge regression with tuning parameter lambda to reduce its complexity. Choose the option(s) below which describes relationship of bias andvariance with lambda.

Which of the following selects the best K high-scorefeatures.

It's possible to specify if the scaling process must include both mean and standard deviation using theparameters .

In many classification problems, the target dataset is made up of categorical labels which cannot immediately be processed by any algorithm. An encoding is needed and scikit-learn offers atleast valid options

which can accept a NumPy RandomStategenerator or an integer seed.

if there is only a discrete number of possible outcomes (called categories),the process becomes a .

During the last few years, many algorithms have been applied to deepneural networks to learn the best policy for playing Atari video games and to teach an agent how to associate the right action with an input representingthe state.

Reinforcement learning is particularly efficient when .

what is the function of ‘Supervised Learning’?

showed better performance than other approaches, even without a context-based model

there's a growing interest in pattern recognition and associative memories whose structure and functioningare similar to what happens in the neocortex. Such an

Techniques involve the usage of both labeled and unlabeled data is called .

When it is necessary to allow the model to develop a generalization ability and avoid a common problemcalled .

In the last decade, many researchers started trainingbigger and bigger models, built with several different layers that's why this approach is called .

In reinforcement learning, this feedback is usually called as .

can be adopted when it's necessary to categorize a large amount of data with a fewcomplete examples or when there's the need to

Linear SVMs have no hyperparameters

100 people are at party. Given data gives information about how many wear pink or not, and if a man or not. Imagine a pink wearing guest leaves, what is the probability of being a man

For the given weather data, what is the probability that players will play if weather is sunny

Linear SVMs have no hyperparameters that need to be set by cross-validation

If I am using all features of my dataset and I achieve 100% accuracy on my training set, but ~70% on validation set, what should I look out for?