Sie sind auf Seite 1von 6

PRESIDENCY UNIVERSITY, BENGALURU

School of Engineering
PROGRAMME –PhD(Computer Science and Engineering)
1 Semester 2018-19
Course Handout

Dated: 19/08/2018
Course Code :
Course Name : STATISTICS AND MACHINE LEARNING
Credit Structure : 3-0-0-0
Instructor-in-charge : Dr.Mohan K
Course Instructors : Dr.Arulmurugan R

1. Learning Objectives and Outcome of the Course

Learning Objectives
1. Solve problems and challenges using statistics with machine learning
approaches.
2. Design and implement various machine learning algorithms in a range
of real-world applications.

Learning Outcomes
After successful completion of the course, student shall be able to
a) Implement Statistics and Probability efficiently for different
applications
b) Apply Binomial Distribution, Normal Distribution, Gaussian
Distribution for Data Classifications
c) Recognize the fundamental issues and challenges of machine learning:
data, model selection, model complexity,
d) Develop Instance based Learning computing technologies that are
suitable for their Research applications

2. Programme Outcome:

On successful completion of the Programme the student shall have:

a) an ability to design a system, component, or process to meet desired needs


within realistic constraints such as economic, environmental, social, political,
ethical, health and safety, manufacturability, and sustainability

b) an ability to identify, formulate, and solve engineering problems

c) an ability to use the techniques, skills, and modern engineering tools necessary
for Research practice

3. Course Description:
This intensive, hands-on Course explores mathematical depend Machine Learning
Approaches. Students will learn Statistics and Basic Probability, Dependence and
Conditional Probability & Bayesian Inference.

1
This Course provide in-depth knowledge in Machine Learning - Applications of
Machine Learning, Uses of Machine Learning - Issues in Machine Learning, Categories
of Machine Learning, Learning Curve, Classification, Error and Noise, Parametric vs
Non-Parametric models – Linear Models Classification and regression using k Nearest
Neighbor - Bayesian decision theory- Classifiers - losses matrix and minimizing risks
–– Logistic regression – Logistic Function – Gradient Descent.

4. Syllabus:

UNIT I

INTRODUCTION TO STATISTICS AND PROBABILITY

Statistics and Basic Probability – Dependent and Independent Random Variables,


Dependence and Conditional Probability & Bayesian Inference, Measure of Center,
Measure of Spread – Variance and Standard Deviation, Sampling Methods.

UNIT II

DISTRIBUTIONS AND MODELING

Probability Distributions – Continuous Distributions-Joint Distributions, Binomial


Distribution, Normal Distribution, Gaussian Distribution, Central Limit Theorem,
Linear Regression Model and Analysis.

UNIT III

FOUNDATIONS OF MACHINE LEARNING

Machine Learning, Machine Learning Foundations, Applications of Machine Learning,


Uses of Machine Learning - Issues in Machine Learning, Categories of Machine
Learning, Learning Curve, Classification, Losses and Risks, Decision regions and
Decision boundaries, Parametric vs Non-Parametric models – Linear Models.

UNIT IV

INSTANCE BASED LEARNING

K-Nearest Neighbor – Introduction – Assumption - Classification and regression using


k Nearest Neighbor - Bayesian decision theory- Classifiers - Logistic regression –
Logistic Function – Gradient Descent – Challenges – Variants.

5. Instructional Pedagogy:

This is an intensive hands-on training based course. Students will be assigned a group
project which will require them to develop a working prototype. Thereby students shall
be working on different modules of projects which will be evaluated in the lab
continuously each week. The method of learning is by practicing in the lab. Students
will be oriented towards the concept using live examples. At times, presentations and
case studies will be used to add to the learning.

6. Books:

2
REFERENCES
1. Kevin P. Murphy, “Machine Learning: A Probabilistic Perspective”, MIT
Press, 2012
2. Christopher M.Bishop, “ Pattern Recognition and Machine Learning”,
Springer, 2006
3. Ethem Alpaydin, “Introduction to Machine Learning”, Prentice Hall of India,
2005
4. Tom Mitchell, "Machine Learning", McGraw-Hill, 1997.
5. Laurene Fausett, "Fundamentals of Neural Networks, Architectures,
Algorithms and Applications”, Pearson Education, 2008
WEB REFERENCES
1. https://www.coursera.org/learn/machine-learning
2. https://machinelearningmastery.com/best-machine-learning-resources-for-
getting-started/
3. https://github.com/josephmisiti/awesome-machine-
learning/blob/master/books.md

7. a. Session Plan: Theory


Session
Learning Objectives Topics to be covered Resources
No.
1 Understand the basics of Statistics and Basic
RB1 Ch:2
Statistics and Probability Probability
2 Intorudcing the required
Dependent and
Mathematical Concepts Independent Random RB1 Ch:2
Variables
3 Intorudcing the required Dependence and
RB1 Ch:2
Mathematical Concepts Conditional Probability
4 Understand the Bayesian Inference
RB1 Ch:3
Bayesian concept learning
5 Know the Measure of Center Measure of Center Web reference
6 Differentiate between Variance and Standard
Variance and Standard Deviation RB1 Ch 2
Deviation
7 Demonstrate the Sampling Sampling Methods RB1 Ch 3
8 Self-Learning Topic Binomial and Bernoulli
distributions
8 Review of Self-learning
9 Learn how to use Probability Probability Distributions Chow, C. K.
Distributions and C. N. Liu
(1968).
Approximating
discrete
probability
distributions
with
dependence
trees. IEEE
Trans. on Info.
Theory 14,
462–67.
10 Learn how to use Continuous
RB1 Ch:2
Continuous Distributions Distributions
3
11 Learn how to use Joint Distributions RB1 Ch:2
Joint Distributions
12 Understand the concept of Binomial Distribution RB1 Ch:2
Binomial Distribution
13 Understand the concept of Normal Distribution RB1 Ch:2
Normal Distribution
14 Explore the knowledge on Gaussian Distribution RB1 Ch:2
Gaussian Distribution
15 Learn concept of Central Limit Central Limit Theorem RB1 Ch:2
Theorem
16 Learn Concept of Linear Linear Regression RB1 Ch:2
Regression Model and Analysis Model and Analysis
17 Apply Dimensionality Dimensionality
RB3
Reduction for Feature sets Reduction-PCA
18 Apply Dimensionality Dimensionality
RB3
Reduction for Feature sets Reduction-LDA
19 Apply Dimensionality Dimensionality
Web Reference
Reduction for Feature sets Reduction-FDA
Self-Learning Topic Two-class LDA RB1
20 Review of Self-learning
21 Know the concept of Machine Machine Learning and
RB3
Learning its Foundations
22 Understand the major
Applications of Machine
Applications of Machine RB1,2,3
Learning
Learning
23 Know the uses of Machine Uses of Machine Web
Learning Learning references
24 Discuss issues in Machine Issues in Machine
RB4
Learning Learning
25 Explore different Categories of Categories of Machine
Learning RB2
Machine Learning
26 Explore different Categories of Supervised Learning RB3
Machine Learning
27 Learn about the Curves Learning Curve RB1
28 Apply the classification
Classification RB3
approach for differentiation
29 Understand the Losses and
Losses and Risks RB3
Risks factor
30 Decision regions and
Know the Decision taking steps RB3
Decision boundaries
31 Understand the Parametric and Parametric vs Non-
RB3
Non-Parametric models Parametric models
Self-study Topic Linear Model RB2
32 Revision on previous topics
33 Apply Instance based Learning
K-Nearest Neighbor RB4
34 Classification and
Apply Instance based Learning regression using k RB4
Nearest Neighbor
35 Bayesian decision
Analyze of Bayesian decision theory RB1
theory
36 Analyze of Bayesian decision The false positive vs
RB1
theory false negative tradeoff
37 Appling Classifiers for data Classifers RB1
evaluation
4
38 Appling Classifiers for data
Naive Bayes classifiers RB1
evaluation
39 Generative vs
Appling Classifiers for data
discriminative RB1
evaluation
classifiers
40 Understand the principles of
Logistic regression RB1
Logistic regression
41 Understand the concept of
Logistic Function RB1
Logistic regression
42 Know about Gradient Descent Gradient Descent RB1
43 Analyzes about Variants Challenges – Variants RB1
44 Know about Steepest Descent Steepest descent RB1
Self-Learning Topic
Linear Gaussian systems Web reference
45
Revision

8. Self-learning topics:

Sl. No. Self-Study Topic Source


1 Binomial and Bernoulli distributions RB1
2 Two-class LDA RB1
3 Linear Model RB2
4 Linear Gaussian systems Web reference

9. Assessments:
Duration % Marks Venue
Component Date & Time
(minutes) Weightage
Seminar Presentation-
using Machine Learning 1 10% 10 Later
Topics
Assignments-1 NA 10% 10 Mid of Semester
Mini Project with case At the End of
NA 40% 40
study Semester
End Term Final *
2 hours 40% 40
Semester Examinations
*
Date, time and venue will be decided by COE

10. Chamber consultation hour: Tuesday 4PM to 5PM

11. Notices: All notices related to the course will be displayed on the Notice Board.
12. Make-Up Policy:
1. No Make-up will be available for any of the assignments.
2. A make-up test shall be granted only in genuine cases where - in the Instructor
In-Charge’s judgment - the student would be physically unable to appear for the
test.
5
Instructor-in-charge

Das könnte Ihnen auch gefallen