Table of Contents

1.If you have a basket of different fruit varieties with some prior information on size, color, shape of each and every fruit . Which learning methodology is best applicable?

a) Supervised Learning

b) Unsupervised Learning

Select the Correct Answer from above Options:

Answer: 1)Supervised Learning

1.Do you think heuristic for rule learning and heuristics for decision trees are both same ?

a) True

b) False

Select the Correct Answer from above Options:

Answer: 2)False

2.Now Can you make quick guess where Decision tree will fall into **_**

a) Supervised Learning

b) Unsupervised Learning

Select the Correct Answer from above Options:

Answer: 1)Supervised Learning

## MCQ on Naïve Bayes Questions on Machine Learning Axioms

1.What is the benefit of Naïve Bayes ?

a) Does not require any data

b) can handle any data volume easily

c) Requires less training data

d) can process faster with any data

Select the Correct Answer from above Options:

Answer: 3)Requires less training data

## MCQ on Gradient Descent Questions on Machine Learning Axioms

1.What is the advantage of using an iterative algorithm like gradient descent ? (select the best)

a) Linear regression problems there is no closed form solution

b) For Nonlinear regression problems, there is no closed form solution

c) Linear regression problems have multiple solutions

d) Select the Correct Answer from above Options:

Answer: 2)For Nonlinear regression problems, there is no closed form solution

## MCQ on Linear Regression Questions on Machine Learning Axioms

1.For which one of these relationships could we use a regression analysis? Choose the correct one

a) Relationship between being part of committee and number of eye operations

b) Relationship between Height & weight (both Quantitative)

c) Relation between age and person is married

d) Relationship between eye color (blue/black) and hair color (grey,blonde)

Select the Correct Answer from above Options:

Answer: 2)Relationship between Height & weight (both Quantitative)

## MCQ on Logistic Regression Questions on Machine Learning Axioms

1.Does Logistic regression check for the linear relationship between dependent and independent variables ?

a) False

b) True

Select the Correct Answer from above Options:

Answer: 1)False

## MCQ on Support Vector Machine Questions on Machine Learning Axioms

1.Which helps SVM to implement the algorithm in high dimensional space?

a) Classification

b) Kernel

c) Logistic Regression

d) Multi-Linear Regression

Select the Correct Answer from above Options:

Answer: 2)Kernel

## MCQ on Kernel Methods Questions on Machine Learning Axioms

1.Kernel methods can be used for supervised and unsupervised problems

a) True

b) False

Select the Correct Answer from above Options:

Answer: 1)True

## MCQ on Neural Networks Questions on Machine Learning Axioms

1.Perceptron is *___*

a) an auto-associative neural network

b) a single layer feed-forward neural network

c) a double layer auto-associative neural network

Select the Correct Answer from above Options:

Answer: 2)a single layer feed-forward neural network

## MCQ on Clustering Questions on Machine Learning Axioms

1.While running the same algorithm multiple times, which algorithm produces same results?

a) Classification Clustering

b) K Means clustering

c) Hierarchical clustering

Select the Correct Answer from above Options:

Answer: 3)Hierarchical clustering

## MCQ Questions on Machine Learning Axioms Final Assessment

1.If the outcome is continuous, which model to be applied?

a) Linear Regression

b) Classification

c) Multi-Linear Regression

d) Logistic Regression

Select the Correct Answer from above Options:

Answer: 1)Linear Regression

2.The model which is widely used for the classification is

a) Logistic Regression

b) Segmentation

c) Linear Regression

d) Multi-Linear Regression

Select the Correct Answer from above Options:

Answer: 1)Logistic Regression

3.Which of them, best represents the property of Kernel?

a) Modularity

b) Scalability

c) Converge

d) Extensibility

Select the Correct Answer from above Options:

Answer: 1)Modularity

4.SVM will not perform well with large data set because (select the best answer)

a) training time is high

b) Difficult to simulate model

c) classification becomes difficult

d) Lot of noise in data

Select the Correct Answer from above Options:

Answer: 1)training time is high

5.What are different types of Supervised learning

a) Naive Bayes & classification

b) regression and classification

c) Segmentation and regression

d) Clustering and regression

Select the Correct Answer from above Options:

Answer: 2)regression and classification

6.SVM uses which method for pattern analysis in High dimensional space?

a) Multi-Linear Regression

b) Kernel

c) Logistic Regression

d) Classification

Select the Correct Answer from above Options:

Answer: 2)Kernel

7.Which type of the clustering could handle Big Data?

a) Hierarchical clustering

b) K Means clustering

Select the Correct Answer from above Options:

Answer: 2)K Means clustering

8.Which of the following is not example of Clustering?

a) Recommendation engines

b) Image segmentation

c) RFM Analysis

d) Anomaly detection

e) Market segmentation

Select the Correct Answer from above Options:

Answer: 3)RFM Analysis

9.Most famous technique used in Text mining is

a) Segmentation

b) Clustering

c) Naive Bayes

Select the Correct Answer from above Options:

Answer: 3)Naive Bayes

10.The main problem with using single regression line

a) Response variable is not appropriate

b) Curvilinear data

c) merging of groups

d) presence of 1 or more outliers

Select the Correct Answer from above Options:

Answer: 4)presence of 1 or more outliers

11.In Kernel trick method, We do not need the coordinates of the data in the feature space

a) False

b) True

Select the Correct Answer from above Options:

Answer: 2)True

12.Effect of outlier on the correlation coefficient *__*

a) decrease the correlation coefficient

b) no effect on a correlation coefficient

c) An outlier might either decrease or increase a correlation coefficient, depending on where it is in relation to the other points

d) increase a correlation coefficient

Select the Correct Answer from above Options:

Answer: 3)An outlier might either decrease or increase a correlation coefficient, depending on where it is in relation to the other points

13.Which model helps SVM to implement the algorithm in high dimensional space?

a) Kernel

b) Multi-Linear Regression

c) Logistic Regression

d) Classification

Select the Correct Answer from above Options:

Answer: 1)Kernel

14.Which technique implicitly defines the class of possible patterns by introducing a notion of similarity between data?

a) SVM

b) Multi-Linear Regression

c) Kernel

d) Hierarchical clustering

e) Linear Regression

Select the Correct Answer from above Options:

Answer: 3)Kernel

15.Consider a regression equation, Now which of the following could not be answered by regression?

a) Predict the value of y at a particular value of x

b) Estimate whether the association is linear or non-linear

c) Estimate whether the linear association is positive or negative

d) Estimate the slope between y and x

Select the Correct Answer from above Options:

Answer: 2)Estimate whether the association is linear or non-linear

16.The model in which one estimates the probability that the outcome variable assumes a certain value, rather than estimating the value itself.

a) Multi-Linear Regression

b) Logistic Regression

c) Classification

d) Linear Regression

Select the Correct Answer from above Options:

Answer: 2)Logistic Regression

17.While running the same algorithm multiple times, which algorithm produces same results?

a) K Means clustering

b) Hierarchical clustering

Select the Correct Answer from above Options:

Answer: 2)Hierarchical clustering

18.If the outcome is binary(0/1), which model to be applied?

a) Classification

b) Logistic Regression

c) Multi-Linear Regression

d) Linear Regression

Select the Correct Answer from above Options:

Answer: 2)Logistic Regression

19.One has to run through ALL the samples in your training set to do a single update for a parameter in a particular iteration. This is applicable for

a) Anomaly detection

b) Gradient Descent

c) stochastic gradient descent

d) Neural Networks

Select the Correct Answer from above Options:

Answer: 2)Gradient Descent

20.What are the advantages of neural networks (i) ability to learn by example (ii) fault tolerant (iii) suited for real time operation due to their high ‘computational’ rates

a) All the options are correct

b) (ii) and (iii) are true

c) (i) and (ii) are true

d) (i) and (iii) are true

Select the Correct Answer from above Options:

Answer: 1)All the options are correct

21.Correlation and regression are concerned with the relationship between *_*

a) quantitative response variable and categorical explanatory variable

b) 2 quantitative variables

c) 2 categorical variables

d) quantitative explanatory variable and categorical response variable

Select the Correct Answer from above Options:

Answer: 2)2 quantitative variables

22.The correlation between two variables is given by r = 0.0. . This means

a) There is a perfect positive relationship between the two variables

b) The best straight line through the data is horizontal.

c) All of the points must fall exactly on a horizontal straight line

d) There is a perfect negative relationship between the two variables

Select the Correct Answer from above Options:

Answer: 2)The best straight line through the data is horizontal.

23.Which clustering technique requires prior knowledge of the number of clusters required?

a) Hierarchical clustering

b) K Means clustering

Select the Correct Answer from above Options:

Answer: 2)K Means clustering

24.Disadvantage of Neural network according to your purview is

a) takes long time to be trained

b) iterations should be defined

c) More nodes to be defined

Select the Correct Answer from above Options:

Answer: 1)takes long time to be trained

25.The standard approach to supervised learning is to split the set of example into the training set and the test

a) True

b) False

Select the Correct Answer from above Options:

Answer: 1)True

26.Which methodology works with clear margins of separation points?

a) Support Vector Machine

b) Multi-Linear Regression

c) Linear Regression

d) Logistic Regression

Select the Correct Answer from above Options:

Answer: 1)Support Vector Machine

27.Which of the learning methodology applies conditional probability of all the variables with respective the dependent variable?

a) Unsupervised Learning

b) Supervised Learning

Select the Correct Answer from above Options:

Answer: 2)Supervised Learning

28.Objective of unsupervised data covers all these aspect except

a) trace interesting directions in data

b) prepare the training data set

c) detect interesting coordinates and correlations

d) find clusters of the data

e) low-dimensional representations of the data

Select the Correct Answer from above Options:

Answer: 2)prepare the training data set

29.SVM will not perform well with data with more noise because (select the best answer)

a) more work involved in removing noise

b) training time is high

c) Difficult to simulate model

d) target classes could overlap

Select the Correct Answer from above Options:

Answer: 4)target classes could overlap