Q1.

Attempt the following

a) What Are the Different Types of Machine Learning Techniques?
b) What is Overfitting in Machine Learning and how can it be avoided?
c) What is ‘training Set’ and ‘test Set’ in a Machine Learning Model? How Much Data Will You Allocate
for Your Training, Validation, and Test Sets?
d) How Do You Handle Missing or Corrupted Data in a Dataset?
e) What Are the Three Stages of Building a Model in Machine Learning?
f) Considering a Long List of Machine Learning Algorithms, given a Data Set, How Do You Decide Which
One to Use?
g) Differentiate between Classification and Regression.
Q2.a)What is Pruning in Decision Trees, and How Is It Done?
b) Consider a two-class classification problem of predicting whether a photograph contains a man or a woman.
Suppose we have a test dataset of 10 records with expected outcomes and a set of predictions from our
classification algorithm.

(i) Compute the confusion matrix for the data.

(ii) Compute the accuracy, precision, recall, sensitivity and specificity of the data.

Q3 a)What do you understand by Type I vs Type II error?

b) Consider the data S given in Table which specify the features of certain vertebrates and the class to which
they belong

i) Let “xxx” be some class label. We denote by pxxx the proportion of examples with class label “xxx”. Calculate
Entropy,
ii)Let S be a set of examples, A be a feature (or, an attribute), Sv be the subset of S with A = v, and Values (A) be
the set of all possible values of A. Calculate the information gain of an attribute A relative to the set S, denoted
by Gain (S, A) .
iii) Calculate the Gini index of S.

Q4a)What are the five statistical measures represented in a boxplot?

b) Using iris dataset ,classify iris flowers using KNN classifier. Write the code and plot confusion matrix
and classification report.
Q 5 a)Consider a set of patients coming for treatment in a certain clinic. Let A denote the event that a “Patient has
liver disease” and B the event that a “Patient is an alcoholic.” It is known from experience that 10% of the
patients entering the clinic have liver disease and 5% of the patients are alcoholics. Also, among those patients
diagnosed with liver disease, 7% are alcoholics. Given that a patient is alcoholic, what is the probability that he
will have liver disease?
b) Use Naive Bayes Algorithm(write the complete code) to determine whether a red domestic SUV car is a
stolen car or not using the following data:

Q.6 Attempt the following

a) Explain various machine Learning Techniques.
b) How Do You Handle Missing or Corrupted Data in a Dataset?
c) Diagrammatically explain ROC curve. How can they be used to assess the performance of a
classifier?
d) Give various applications of Machine Learning.
e) What is Overfitting in Machine Learning and how can it be avoided?
f) What is K fold Cross-validation in Machine Learning?
g) Differentiate Linear and Logistic Regression.
h) Explain Pre Pruning and Post Pruning techniques .
Q.7 (a) Explain in brief binary, multi-class, multi-label, and imbalanced classifications (b)
Consider a problem of predicting whether a photograph contains a man or a woman.
 Below is the table showing expected and predicted outcome.

(i) Compute the confusion matrix for the data.

(ii) Compute the accuracy, precision, recall, sensitivity and specificity of the data.

Q.8 (a) Explain working of Random Forest algorithm, give its complete python code. Specify its Pros
and Cons.
(b) What is a Decision tree? Explain Entropy, Information gain and Gini impurity/index with
formula for each.
Q.9(a) Explain the working of Naïve Bayes' Classifier. Consider the data file of email “spam.csv”
having two columns Category and Message, classify the emails into two categories spam (good email)
and ham (bad email). Give the complete code.
(b) What is curse of Dimensionality Reduction? How PCA is used of Dimensionality Reduction?

Q10. (a) Give the complete implementation of KNN classifier on ‘iris.csv’ dataset (Sepal Length, Sepal
Width, Petal Length, Petal Width) also write the code for plotting confusion matrix and classifier
Report.
(b) What is the objective of K Means method. How does the K-Means algorithm work.Give its
complete code

Q. 11 (a) Describe the following

(i) Life cycle of Machine learning.
(ii) Self-Organizing Map
(iii) Various Clustering Methods.
Q.12 Attempt the following
a) Give Application of Machine learning.
b) Explain the reason for overfitting and underfitting problems in machine Learning and the ways
to deal with it.
c) Explain PCA.
d) Explain in brief binary, multi-class, multi-label, and imbalanced classifications.
e) What are outliers. Specify methods to deal with outliers.
f) Differentiate Single layer and Multi- layered perceptron.
g) Explain two ensemble learning models.

Q.13 (a) Under what circumstances Precision, or Recall are better performance metrics in comparison with
Accuracy? Give an example each for the situations where “Recall is a more important evaluation metric than
Precision”and “Precision is a more important evaluation metric than Recall”
(b) What is a Decision tree? Explain its
advantage and disadvantage. By taking example explain
Entropy, Information gain and Gini impurity.

Q14. (a) Explain Support Vector Machine. Define the terms Hyperplane, Support Vectors, Kernel, Hard
and Soft Margin.
(b) What is Activation functions? Explain any three
Q15 (a) Explain Gradient Descent and its types. What are the different steps used in Gradient Descent Algorithm.

(b) What do you mean by Feature selection? Explain various methods of feature selection.

Q16. (a) Explain various clustering methods. Explain k means clustering algorithm with example
(b) Explain k nearest neighbor algorithm.

Q17 Explain the following

(i)SOP
(ii)Dimensionality reduction
(iii)Random forest algorithm

Q.18 Attempt the following

a) Explain Machine Learning, Artificial Intelligence, and Deep Learning
b) How Do You Handle Missing or Corrupted Data in a Dataset?
c) Explain the ROC curve and AUC score. How can they be used to assess the performance of a
classifier?
d) Give applications of Machine Learning in detail.
e) What is the Back Propagation Learning Algorithm?
f) What is Cross-validation in Machine Learning?
g) What is Pruning in Decision Trees, and How Is It Done?
h) Explain Activation Functions used in Neural Networks.

Q.19 (a) Diagrammatically explain life cycle of Machine learning.

(b) Consider a two-class classification problem of predicting whether a photograph contains a
man or a woman. Suppose we have a test dataset of 10 records with expected outcomes and a
set of predictions from our classification algorithm.

(i) Compute the confusion matrix for the data.

(ii) Compute the accuracy, precision, recall, sensitivity and specificity of the data.

Q.20 (a) Explain in brief binary, multi-class, multi-label, and imbalanced classifications.
(b) What is the difference between linear and logistic regression? When would you use logistic
regression instead of linear regression?
 Q 21 (a) What is a Decision tree? Explain its advantage and disadvantage. By taking example
explain Entropy, Information gain and Gini impurity with formula for each.
(b)How does Random Forest algorithm work, give its complete code. Give its advantage and
Applications.

Q22 (a) Explain the working of Naïve Bayes' Classifier. For the file “spam.csv” of emails , classify
the emails into two categories spam(good email) and ham(bad email).

(b) Give the complete implementation of KNN classifier also write the code for plotting
confusion matrix and classifier Report

Q. 23 (a)What is the role of the Activation functions in Neural Networks? Explain any two
(b)Explain ANN diagrammatically. Give its advantage and disadvantage.

Q. 24 (a)Explain the need and working of Backpropagation technology.

(b)Give Steps to prevent overfitting of a neural network

Q. 25 (a) Describe the following

(i) PCA in Machine Learning.
(ii) Self-Organizing Map

Q. 26 (a)What is the difference between supervised and unsupervised learning, and where does
clustering fit in? Describe various clustering techniques briefly.
(b)What is the objective of K Means method. How does the K-Means algorithm work.Give its
complete code.

Q.27 Attempt the following

a. Diagrammatically explain life cycle of Machine learning.
b. Explain the reason for overfitting and underfitting problems in machine Learning and
the ways
to deal with it.
c. What is ROC curve? How is it constructed?
d. Explain confusion Matrix.
e. Explain in brief binary, multi-class, multi-label, and imbalanced classifications.
f. What are outliers. Specify methods to deal with outliers.
 g. What is Bias and Variance in a Machine Learning Model

Q.28 (a) What is difference between Linear and Logistic Regression. Consider a file “home .csv”,
build a machine learning model that can predict home prices based on square feet area
using Linear regression. Give the complete code in python.

(b) Give applications of Machine Learning in detail.

Q.29 (a) Consider a binary classification problem of car making company that has recently launched a
new SUV car. So the company wanted to check how many users from the dataset, wants to
purchase the car. Build a Machine Learning model using the Logistic regression algorithm that
will predict the purchased variable (Dependent Variable) by using age and salary
(Independent variables).Given below is sample data set “carpurchase.csv”.

(b) Explain various types of Machine Learning .

Q.30 (a) What is a Decision tree? Explain its advantage and disadvantage. By taking example explain
Entropy, Information gain and Gini impurity.
(b) What is Pruning in Decision Trees, and How Is It Done?

Q31 (a) Explain the working of Naïve Bayes' Classifier. For the file “spam.csv” of emails , use
MultinomialNB and classify the emails into two categories spam(good email) and ham(bad
email).

(b) Explain Support Vector Machine. Define the terms Hyperplane, Support Vectors, Kernel,
Hard and Soft Margin.
 Q. 32 (a)What is the role of the Activation functions in Neural Networks? Give the names of
three popular Activation Functions used in Neural Networks.
(b)Explain hebbian learning rule. Implement AND gate using hebbian rule.

Q. 33 (a) Explain Gradient Descent and its types. What are the different steps used in Gradient
Descent Algorithm.
(b)Differentiate Single layer and Multi- layered perceptron

Q.34 (a)Explain the following

(i) PCA in Machine Learning.
(ii) Random Forest Algorithm

(b)What do you mean by Feature selection? Explain Filter methods, Wrapper methods
and
Embedded methods of feature selection.

Q. 35 (a)Explain various clustering methods. Explain k means clustering algorithm with

Example.
(b)Describe the following in relation with machine learning
(i)Cross-Validation
(ii)Dimensionality reduction
(iii)Ensemble Learning