Beruflich Dokumente
Kultur Dokumente
Course Objective: Course aims at building intelligent machines to solve real-world problems by
selecting suitable methods and Machine Learning algorithms. It also focus on advanced Machine
Learning and Computing technique such as Machine Learning Perception, Supervised Learning,
Unsupervised & Semi-Supervised Learning, Structured Models and Feedforward Networks for
Classification with simulation. It is predicted that in future Machine Learning is going to become
a globally recognized area and will be applied extensively in all the fields.
Course Rationale:
In this course provides, various machine learning algorithms, underlying concepts and their application to a
real-world problem. It clears the idea of Machine Learning as one such a course which deals with making
machines more powerful and intelligent. Finally, it helps the signal detection/ prediction using Machine
learning techniques and Understand the concepts of Unsupervised and semi-supervised Learning with
industrial applications.
PO
keyword Program Outcome Description
No
An ability to apply knowledge of mathematics, science, engineering
Engineering
1 fundamentals and an engineering specialization for the solution of
Knowledge
complex engineering problems in Mechanical engineering
An ability to identify, formulate, research literature, analyse complex
Problem
2 engineering problems in mechanical engineering using first principles of
Analysis
mathematics, natural sciences and engineering sciences
Design/ An ability to design solutions for complex engineering problems and
3 development system component or processes that meet the specified needs considering
of solutions public health & safety and cultural, societal & environment
PSO
Program Specific Outcome Description
No
An ability to Understand the theoretical and mathematical concepts to analyze real time
1
problems.
SYLLABUS:
Introduction: Definition of learning systems. Goals and applications of machine learning. Aspects
of developing a learning system: training data, concept representation, function approximation.
Machine Learning Perception: Learning from data, Overfitting, regularization, cross-validation
Supervised Learning: Nearest Neighbour, Naive Bayes, Logistic Regression, Support Vector Machines, Neural
Networks, Decision Trees.Unsupervised & Semi-Supervised Learning: Clustering (K-means, GMMS),
Factor Analysis (PCA, LDA), Learning Theory: Bias and Variance, Probably Approximately Correct (PAC)
Learning.
Structured Models: Bayesian Network, Hidden Markov Models, Reinforcement Learning, Applications of ML
to Perception: Computer Vision, Natural Language Processing, Design and implementation Machine Learning
Algorithms,
Feedforward Networks for Classification, Convolutional Neural Network based Recognition using Keras,
Tensorflow and OpenCV. Simulation: Use VGG Net and AlexNet pre-trained models for face recognition and
human pose estimation problems.
Text Books:
1.Tom M. Mitchell,” Machine Learning”, Indian Edition, McGraw Hill,1997.
2. MacKay, David. Information Theory, Inference, and Learning Algorithms. Edition;Version 7.2 (fourth
printing)Cambridge, UK: Cambridge University Press, 2003.
Reference Books:
1. Bishop, Christopher. Neural Networks for Pattern Recognition. Edition: A Clarendon Press Publication,
Oxford University Press, New York, NY,1995.
2. Duda, Richard, Peter Hart, and David Stork. Pattern Classification. 2nd Edition, Wiley-
Intercedence, New York, 2000.
3. Hastie, T., R. Tibshirani, and J. H. Friedman. The Elements of Statistical Learning: Data mining, Inference
and Prediction. New York, NY: Springer, 2001. ISBN: 9780387952840.
Web References/MOOCS:
1. https://www.coursera.org/specializations/machine-learning
2. https://www.coursera.org/learn/machine-learning
3. https://in.udacity.com/course/machine-learning-engineer-nanodegree--nd009t
4. https://www.udemy.com/machinelearning/
COURSE DELIVERY PLAN:
Session Number: 1
Session Outcome: The Student will be able to understand the overview of the course and its various components
Time Teaching–
Topic BTL Learning
(Min) Active Learning Method
Method
50 Course Handout --
PPT
Session Number: 2
Session Outcome: Students will be able to understand the significance of ML in solving real world
applications
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Introduction 1 Discussion
Think/
pair/share
10 Machine Learning 1
Chalk and Talk,PPT
20 Computing Techniques 1
Chalk and Talk,PPT
10 List of Applications of ML 1 Chalk and Talk,PPT
05 Conclusion & Summary
Chalk and Talk,PPT
Session Number: 3
Session Outcome: Students will be able to understand the significance of Definition of learning
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1 Discussion
10 Definition of learning systems 1
Chalk and Talk,PPT
Think/
pair/share
20 List of Applications of ML 1
Chalk and Talk,PPT
10 Well-posed learning Problems 1 Chalk and Talk,PPT
05 Conclusion & Summary
Chalk and Talk,PPT
Session Number: 4
Session Outcome: Students will be able to understand the Goals of the Machine Learning
Teaching–
Time(min) Topic BTL Learning Method Active Learning
Method
05 Recap 1 Discussion
10 Goals of the Machine Learning 1
Chalk and Talk,PPT
Think/
pair/share
20 List of Goals of the Machine Learning 1
Chalk and Talk,PPT
10 Discussion of Goals of Machine Learning 1 Chalk and Talk,PPT
05 Conclusion & Summary
Chalk and Talk,PPT
Session Number: 5
Session Outcome: Students will be able to understand the Aspects of developing a learning system
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1 Chalk and Talk,PPT
20 Aspects of developing a learning 1 Chalk and Talk,PPT Think/
system pair/share
10 Discussion with methods of it 1 Chalk and Talk,PPT
10 Well-posed learning Problems 2 Chalk and Talk,PPT
05 Conclusion & Summary Chalk and Talk,PPT
Session Number: 6
Session Outcome: Students will be able to understand the training data, developing a learning system
20
training data, developing a learning 2
Chalk and Talk,PPT
Think/
system pair/share
15 Well-posed learning Problems 2 Chalk and Talk,PPT
5 Conclusion & Summary 2
Chalk and Talk,PPT
Session Number: 7
Session Outcome: Students will be able to understand the Concept Representation, function approximation
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1
Discussion
10 Concept Representation, 2
Chalk and Talk,PPT
Think/
pair/share
20 function approximation 2 Chalk and Talk,PPT
10 Well-posed learning Problems 2
Chalk and Talk,PPT
05 Conclusion & Summary 1
Chalk and Talk,PPT
Session Number: 8
Session Outcome: Students will be able to understand the Machine Learning Perception:
Introduction
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1
Discussion
10 Machine Learning Perception: 2
Chalk and Talk,PPT
Think/
Introduction pair/share
20 2 Chalk and Talk,PPT
10 Well-posed learning Problems 2
Chalk and Talk,PPT
05 Conclusion & Summary 1
Chalk and Talk,PPT
Session Number: 9
Session Outcome: Students will be able to understand the Learning from data, Overfitting
Regularization, cross-validation 2
20 Chalk and Board
Well-posed learning Problems
20 Chalk and Board One-
3 Minute
quaries
1
05 Conclusion & Summary Chalk and Board
Session Number: 11
Session Outcome: Students will be able to understand the Supervised Learning: Introduction
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1 Discussion
10 Supervised Learning: Introduction 1
Chalk and Talk,PPT
Think/
pair/share
20 1
Chalk and Talk,PPT
10 Well-posed learning Problems 2 Chalk and Talk,PPT
05 Conclusion & Summary
Chalk and Talk,PPT
Session Number: 12
Session Outcome: Students will be able to understand the Nearest Neighbour
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1 Discussion
10 Nearest Neighbour 1
Chalk and Talk,PPT
Think/
pair/share
20 Advantages and Disadvantages 1
Chalk and Talk,PPT
10 Well-posed learning Problems 2 Chalk and Talk,PPT
05 Conclusion & Summary
Chalk and Talk,PPT
Session Number: 13
Session Outcome: Students will be able to understand the Naive Bayes
Teaching – Learning Active Learning
Time(min) Topic BTL
Method Method
05 Recap 1 Discussion
20
Naive Bayes 1 Chalk and Board Think
/
pair/s
hare
Well-posed learning Problems 2
20 Chalk and Board
Session Number: 14
Session Outcome: : students explains the Logistic Regression
Teaching – Learning Active Learning
Time(min) Topic BTL
Method Method
Recap 1
05 Discussion
Logistic Regression 2 Think
20 Chalk and Board
/
pair/s
hare
Decision Logistic function Representation
20 3 Chalk and Board
1
05 Conclusion & Summary Chalk and Board
Session Number: 15
Session Outcome: Students will be able to understand the Support Vector Machines
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1
Discussion
10 Support Vector Machines 2
Chalk and Talk,PPT
Advantages and Disadvantages Chalk and Talk,PPT Questions and
20 3
Answers
10 Well-posed learning Problems 1
Chalk and Talk,PPT
05 Conclusion & Summary 1
Chalk and Talk,PPT
Session Number: 16
Session Outcome: Students will be able to understand the Neural Networks, Decision Trees
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1
Discussion
10 Neural Networks, Decision Trees 2
Chalk and Talk,PPT
20 Decision tree Representation 3 Chalk and Talk,PPT
10 Well-posed learning Problems 1 Questions and
Chalk and Talk,PPT Answers
05 Conclusion & Summary 1
Chalk and Talk,PPT
Session Number: 17
Session Outcome: Students should able to apply Unsupervised & Semi-Supervised Learning:, , Learning Theory
Teaching – Learning Active Learning
Time(min) Topic BTL
Method Method
05 Recap 1 Discussion
Session Number: 18
Session Outcome: Students should able to understand the Clustering (K-means)
Teaching – Learning Active Learning
Time(min) Topic BTL
Method Method
Recap
05 1 Discussion
20
Clustering (K-means) 2 Chalk and Talk,PPT Think/
pair/share
Advantages and Disadvantages
10 2 Chalk and Talk,PPT
Session Number: 19
Session Outcome: Students should able to understand Clustering :GMMS,
Teaching – Learning Active Learning
Time(min) Topic BTL Method Method
Recap
05 1 Discussion
Clustering :GMMS, Thin
20 2 Chalk and Board
k/
pair/s
hare
Well-posed learning Problems
20 2 Chalk and Board
Session Number: 20
Session Outcome: Students will be able to understand the Factor Analysis ,PCA
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1
Discussion
10 Factor Analysis ,PCA 2
Chalk and Talk,PPT
Think/
pair/share
20 Example on PCA 3 Chalk and Talk,PPT
10 Well-posed learning Problems 1
Chalk and Talk,PPT
05 Conclusion & Summary 1
Chalk and Talk,PPT
Session Number: 21
Session Outcome: Students will be able to understand the Factor Analysis ,LDA
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1
Discussion
10 Factor Analysis ,LDA 2
Chalk and Talk,PPT
Think/
pair/share
20 Example on LDA 3 Chalk and Talk,PPT
10 Well-posed learning Problems 1
Chalk and Talk,PPT
05 Conclusion & Summary 1
Chalk and Talk,PPT
Session Number: 22
Session Outcome: Students will be able to understand the Bias & Variance,
Teaching – Learning Active Learning
Time(min) Topic BTL
Method Method
05 Recap 1 Discussion
Bias & Variance,
20 2 Chalk and Board Thin
k/
pair/s
hare
20 Well-posed learning Problems 2 Chalk and Board
Session Number: 23
Session Outcome: Students will be able to understand the Bayesian Network,
Teaching – Learning Active Learning
Time(min) Topic BTL
Method Method
Recap
05 1 Discussion
10
Bayesian Network, 2 Chalk and Board Thin
k/
pair/s
hare
30 Well-posed learning Problems 2 Chalk and Board
Session Number: 24
Session Outcome: Students will be able to understand the Probably Approximately Correct (PAC) Learning
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1
Discussion
10 Probably Approximately Correct (PAC) 2
Chalk and Talk,PPT
Learning
Describing the method of PAC Chalk and Talk,PPT
20 3
10 1 Peer Review
Well-posed learning Problems Chalk and Talk,PPT
05 Conclusion & Summary 1
Chalk and Talk,PPT
Session Number: 20
Session Outcome: Students will be able to understand the Structured Models: Introduction
Session Number: 26
Session Outcome: student will be able to Understand the Hidden Markov Models,
Session Number: 27
Session Outcome: student will be able to Understand the Reinforcement Learning
Teaching – Learning Active Learning
Time(min) Topic BTL Method Method
05 Recap 1 Discussion
Reinforcement Learning, 2
15 Chalk and Board Thin
k/
pair/s
hare
25 Describing the method of it Chalk and Board
2
05 Conclusion & Summary 1 Chalk and Board
Session Number: 28
Session Outcome: student will be able to Understand the Applications of ML to Perception
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1
Discussion
10 Applications of ML to Perception 2
Chalk and Talk,PPT
Describing the method of Perceptron optimal Chalk and Talk,PPT Think/
20 2
Classifier pair/share
10 Well-posed learning Problems 3
Chalk and Talk,PPT
05 Conclusion & Summary
Chalk and Talk,PPT
Session Number: 29
Session Outcome: student will be able to Understand the Computer Vision,
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1
Discussion
10 Computer Vision, 2
Chalk and Talk,PPT
Think/
pair/share
20 Applications of it 2 Chalk and Talk,PPT
10 Well-posed learning Problems 3
Chalk and Talk,PPT
05 Conclusion & Summary 1
Chalk and Talk,PPT
Session Number: 30
Session Outcome: student will be able to Understand Genetic Programming
Teaching – Learning Active Learning
Time(min) Topic BTL Method Method
05 Recap 1 Discussion
20 Natural Language Processing, 3 Chalk and Board Thin
k/
pair/s
hare
20 Well-posed learning Problems 2 Chalk and Board
05 Conclusion & Summary 1 Chalk and Board
Session Number: 31
Session Outcome: student will be able to apply Design and implementation Machine Learning
Algorithms,
Teaching – Learning Active Learning
Time(min) Topic BTL Method Method
05 Recap 1 Discussion
Design and implementation Machine
10 Learning Algorithms, 3 Chalk and Board
10 Discussion with Algorithms 3 Chalk and Board Video-
discussions
and
submission
to LMS
Well-posed learning Problems
20 3 Chalk and Board
Session Number: 32
Session Outcome: Students will be able to understand the Feedforward Networks
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1
Discussion
10 Feedforward Networks 2
Chalk and Talk,PPT
Think/
pair/share
20 Discussion with Architecture 2 Chalk and Talk,PPT
10 Well-posed learning Problems 3
Chalk and Talk,PPT
05 Conclusion & Summary
Chalk and Talk,PPT
Session Number: 33
Session Outcome: Students will be able to understand the Feedforward Networks for Classification
Session Number: 34
Session Outcome: Students will be able to understand the CNN
Session Number: 35
Session Outcome: Student will be able to understand Tensor flow and OpenCV
Teaching – Learning Active Learning
Time(min) Topic BTL
Method Method
05 Recap 1 Discussion
10 Tensor flow and OpenCV 2 Chalk and Talk,PPT Think/
pair/share
15 Discussion with Algorithms 2 Chalk and Talk,PPT
Session Number: 36
Session Outcome: Students will be able to understand the Simulation: Use VGG Net
Teaching – Learning Active Learning
Time(min) Topic BTL Method Method
05 Recap 1
Discussion
20 Simulation: Use VGG Net 2
Chalk and Talk,PPT
Think/
10 Discussion with Algorithms 2 Chalk and Talk,PPT pair/share
3
10 Well-posed learning Problems Chalk and Talk,PPT
05 Conclusion & Summary
Chalk and Talk,PPT
Session Number: 37
Session Outcome: Students will be able to understand the Alex Net pre-trained models for face recognition
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1
Discussion
10 Alex Net pre-trained models for face 2
Chalk and Talk,PPT
Think/
recognition pair/share
20 Discussion with Algorithms 2 Chalk and Talk,PPT
10 Well-posed learning Problems 3
Chalk and Talk,PPT
05 Conclusion & Summary 1
Chalk and Talk,PPT
Session Number: 38
Session Outcome: Students will be able to understand the human pose estimation problems.
Session Number: 39
Session Outcome: All topics are revise
Teaching– Active Learning
Time(min) Topic BTL Learning Method Method
05 Recap 1
Discussion
10 All topics are revise 2
Chalk and Talk,PPT
20 Discussion with questions 2 Chalk and Talk,PPT
10 Well-posed learning Problems 3 Quiz
Chalk and Talk,PPT
05 Conclusion & Summary
Chalk and Talk,PPT
WEEKLY HOMEWORK ASSIGNMENTS/ PROBLEM SETS/OPEN ENDEDED PROBLEM- SOLVING
EXERCISES ETC.
2 A01 Machine List out the current areas which are untouched by CO1
Learning and machine learning and what machine learning
Application techniques can be applicable to those area.
4 A02 Clustering Explain the Distance-based model for Clustering with CO2
Industry applications
6 A03 Hidden How Hidden Markov Models can be used for Speech CO3
Markov Recognition applications.
Model
SELF-LEARNING:
Hour 1 2 3 4 5 6 7
Day Component
Mon Theory
Tue Theory
Wed Theory
Lab
Fri Theory
Sat Theory
Evaluation:
\
COURSE TEAM MEMBERS, CHAMBER CONSULTATION HOURS AND CHAMBER VENUE
DETAILS:
Chamber
Chamber Chamber Signature
S. Consultation
Name of Faculty Consultation Consultatio of Course
No Timings for
Day(s) n Room No: faculty
each day
1 Dr.PVV Kishore All days L703
2 Dr. B. Polaiah All days R102
3 Mr.Medikonda Venkata Srinu All days R304
4 SK. Shakwela All days R404