B.E. Elective - II Machine Learning-Mumbai-December 2019 - Grad Plus

B.E. Elective – II Machine Learning-Mumbai-December 2019

MUMABI UNIVERSITY

Subject: Elective – II Machine Learning

Semester: 6

[Total Time: 3 Hours
[Total Marks: 80]
N.B. : 1) Question No. 1 is compulsory.
          2) Attempt any three questions out of the remaining five


Q. 1 a) Define Machine Learning and Explain with example the importance of Machine Learning. (5M)

b) Explain Multilayer perceptron with a neat diagram. (5M)

c) Why is SVM more accurate than logistic regression? (5M)

d) Explain Radial Basis Function with example. (5M)

Q. 2. (a) What is Dimensionality Reduction? Describe how Principal Component Analysis is carried out to reduce the dimensionality of data sets. (10M)

b) Find the singular value decomposition of. (10M)
A=\begin{bmatrix}2&2\\-1&1\end{bmatrix}

Q. 3 a) For an unknown tuple t =<Outllook =Sunny, Temperature =Cool, Wind= Strong> use naïve Bayes classifier to find whether the class for PlayTennis is yes or no. The dataset is given below. (10M)

Outlook Temperature Wind Play Tennis
Sunny Hot Weak No
Sunny Hot Strong No
Overcast Hot Weak Yes
Rain Cool Weak Yes
Rain Cool Strong Yes
Overcast Cool Strong Yes
Sunny Mild Weak No
Sunny Cool Weak Yes
Rain Mild Strong Yes
Sunny Mild Strong Yes
Overcast Mild Strong Yes
Overcast Hot Weak Yes
Rain Mild Strong No

b) List some advantages of derivative-based optimization techniques. Explain Steepest. Descent method for optimization. (10M)

Q. 4. a) Given the following data for the sales of a car of an automobile company for six consecutive years. Predict the sales for the next two consecutive years.

Years 2013 2014 2015 2016 2017 2018
Sales 110 100 250 275 230 300

b) Explain various basic evaluation measures of supervised learning Algorithms for Classification. (10M)

Q. 5 a) Consider the following table for binary classification. Calculate the root of the decision tree using the Gini index. (10M)

Customer Income Gender Car Type Class
High M Family C1
High M Sports C1
High M Family C2
Low M Family C2
Low F Family C2
Low F Sports C1
Low F Sports C1
High M Family C1
High F Family C2
High F Family C2
High F Sports C2
Low M Family C2
Low F Family C2
Low M Sports C1

b) Define Support Vector Machine. Explain how margin is computed and optimal hyper-plane is decided. (10M)

Q. 6. Write Short notes on any four. (20M)

a) Hidden Markov Model

b) EM Algorithm

c) Logistic Regression

d) McCulloch-Pitts Neuron Model

e) DownHill simplex method.
____________________________________________________________________________________________________________________________

Scroll to Top

NAGPUR UNIVERSITY

PUNE UNIVERSITY

MUMBAI UNIVERSITY