NOIDA INSTITUTE OF ENGINEERING AND TECHNOLOGY

GREATER NOIDA-201306
(An Autonomous Institute)
School of Computer Science in Emerging Technologies
B. TECH THIRD YEAR

Course Code BCSML0555 L T P Credits

Course Title MACHINE LEARNING [0-0-6] 3

Course objective: To introduction to the fundamental concepts in machine learning and popular machine learning
algorithms. To understand the standard and most popular supervised learning algorithm

Pre-requisites: Basic Knowledge of Machine learning.

Course Contents / Syllabus

UNIT-I INTRODUCTION TO MACHINE LEARNING 8 Hours
Introduction, Components of Learning, Learning Models, Geometric Models, Probabilistic Models, Logic Models,
Grouping and Grading, designing a Learning System, Types of Learning, Supervised, Unsupervised,
Reinforcement, Perspectives and Issues, Version Spaces, PAC Learning, VC Dimension. Introduction to Model
Building, Sensitivity Analysis, Underfitting and Overfitting, Bias and Variance, Concept Learning Task, Issues in
Machine Learning and Data Science Vs Machine Learning.
Module 2 Supervised and Unsupervised Learning 08 hours
Decision Trees: ID3, Classification and Regression Trees, Regression: Linear Regression, Multiple Linear
Regression, Logistic Regression, Neural Networks: Introduction, Perception, Multilayer Perception, Support
Vector Machines: Linear and Non-Linear, Kernel Functions, K Nearest Neighbors. Introduction to clustering, K-
means clustering, K-Mode Clustering.
Apriori Algorithm: Market basket analysis, Association Rules.
Module 3 ENSEMBLE AND PROBABILISTIC LEARNING 08 hours
Model Combination Schemes, Voting, Error-Correcting Output Codes, Bagging: Random Forest Trees,
Boosting: Adaboost, Stacking. Gaussian mixture models - The Expectation-Maximization (EM) Algorithm,
Information Criteria, Nearest neighbour methods - Nearest Neighbour Smoothing, Efficient Distance
Computations: the KD-Tree, Distance Measures.
Module 4 REINFORCEMENT LEARNING AND EVALUATING HYPOTHESES 08 hours
Introduction, Learning Task, Q Learning, Nondeterministic Rewards and actions, temporal-difference learning,
Relationship to Dynamic Programming, Active reinforcement learning, Generalization in reinforcement
learning. Motivation, Basics of Sampling Theory: Error Estimation and Estimating Binomial Proportions, The
Binomial Distribution, Estimators, Bias, and Variance.
Module 5 GENETIC ALGORITHMS AND CASE STUDIES 08 hours

Motivation, Genetic Algorithms: Representing Hypotheses, Genetic Operator, Fitness Function and Selection,
An Illustrative Example, Hypothesis Space Search, Genetic Programming, Models of Evolution and Learning:
Lamarkian Evolution, Baldwin Effect, Parallelizing Genetic Algorithms.
Case Study: Health Care, E Commerce, Smart Cities.
Course outcome: After completion of this course students will be able to
 Understanding utilization and implementation proper machine
CO1 K2
learning algorithm.
Understand the basic supervised machine learning algorithms.
CO2 K2
Understand the difference between supervise and unsupervised
CO3 K2
learning.
Understand algorithmic topics of machine learning and
mathematically deep K2
CO4
enough to introduce the required theory.
CO5 Apply an appreciation for what is involved in learning from data. K3
Text books:
1. Marco Gori , Machine Learning: A Constraint-Based Approach, Morgan Kaufmann. 2017
2. Ethem Alpaydin, Machine Learning: The New AI, MIT Press-2016
3. Bishop, Christopher. Neural Networks for Pattern Recognition. New York, NY: Oxford University
Press, 1995
4. Tom M. Mitchell, “Machine Learning”, McGraw-Hill, 2010
Reference Books:
1. Ryszard, S., Michalski, J. G. Carbonell and Tom M. Mitchell, Machine Learning: An Artificial
Intelligence Approach, Volume 1, Elsevier. 2014
2. Stephen Marsland, Taylor & Francis 2009. Machine Learning: An Algorithmic Perspective.
3. Ethem Alpaydin, (2004) “Introduction to Machine Learning (Adaptive Computation and Machine
Learning)”, The MIT Press.
4. Fundamentals of Machine Learning for Predictive Data Anayltics: Algorithms, Worked Examples, and
Case Studies 1st Edition by John D. Kelleher
Links: NPTEL/You Tube/Web Link
Unit 1 https://www.youtube.com/watch?v=fC7V8QsPBec&list=PL1xHD4vteKYVpaIiy295pg6_SY 5
qznc77&index=2
Unit 2 https://www.youtube.com/watch?v=OTAR0kT1swg&list=PL1xHD4vteKYVpaIiy295pg6_S
Y5qznc77&index=3
https://www.youtube.com/watch?v=OCwZyYH14uw
https://www.youtube.com/watch?v=9_LY0LiFqRQ
https://www.youtube.com/watch?v=EYeF2e2IKEo
https://www.youtube.com/watch?v=_PwhiWxHK8o
https://www.youtube.com/watch?v=wTF6vzS9fy4
https://www.youtube.com/watch?v=lt65K-REdHw
Unit 3 https://www.youtube.com/watch?v=HTSCbxSxsg&list=PL1xHD4vteKYVpaIiy295pg6_SY5
qznc77&index=4
https://www.youtube.com/watch?v=NnlS2BzXvyM
https://www.youtube.com/watch?v=7enWesSofhg
Unit 4 https://youtu.be/rthuFS5LSOo
https://youtu.be/kho6oANGu_A
Unit 5 https://www.youtube.com/watch?v=9vMpHk44XXo&list=PL1xHD4vteKYVpaIiy295pg6_S
Y5qznc77&index=5
Reinforcement Learning Tutorial | Reinforcement Learning Example Using Python | Edureka -
 YouTube
Association Rule Mining – Solved Numerical Question on Apriori Algorithm(Hindi) - YouTube
Q Learning Explained | Reinforcement Learning Using Python | Q Learning
in AI | Edureka - YouTube
CO
Sr. No. Program Title
Mapping
Data Preprocessing and Feature Selection on Titanic Dataset CO1
• Handle missing values (impute or drop)
• Encode categorical variables (LabelEncoder or OneHotEncoder)
1 • Normalize or standardize numerical features
• Split dataset into training and testing sets
Perform correlation analysis for feature selection

Regression Techniques on Boston Housing Dataset CO2

• Implement Simple Linear Regression (one feature vs. target)
• Implement Multiple Linear Regression (all features vs. target)
2 • (Optional) Polynomial Regression for non-linear relationships
• Visualize model fits using matplotlib/seaborn
Evaluate models using MSE, RMSE, and R² score

Logistic Regression for Binary and Multiclass Classification on Iris CO2

Dataset
• Binary classification (Setosa vs. Versicolor) using Logistic
3 Regression
• Visualize decision boundary
• Evaluate accuracy, precision, recall, F1-score
Extend to multiclass classification using One-vs-Rest strategy

Decision Tree Classification (CART & ID3) on Wine Dataset CO2

• Train Decision Tree classifiers using DecisionTreeClassifier
4 • Visualize decision tree with plot_tree or graphviz
Perform hyperparameter tuning (max_depth, min_samples_split) using
GridSearchCV

Support Vector Machines (SVM) for Classification and Regression CO2

• Generate synthetic datasets (make_moons or make_circles)
• Train SVM with linear and RBF kernels; visualize decision
boundaries
5 • Hyperparameter tuning for C and gamma using cross-validation
• Apply SVM on Breast Cancer dataset and evaluate performance
Implement Support Vector Regression (SVR) with linear and RBF
kernels
 K-Nearest Neighbors (K-NN) Classification CO2
• Train K-NN classifier on labeled dataset
• Experiment with varying k and distance metrics (Euclidean,
6 Manhattan)
Evaluate with cross-validation and classification metrics (accuracy,
precision, recall)

Clustering using K-Means and Expectation-Maximization (EM) CO2

• Apply K-Means and Gaussian Mixture Model (EM algorithm) on
dataset
7 • Use Elbow Method and Silhouette Coefficient to find optimal
clusters
Visualize clusters with scatter plots or pairplots

Hierarchical Clustering Techniques CO3

• Perform Agglomerative (AGNES) and Divisive (DIANA)
clustering
8 • Use linkage criteria: single, complete, average
• Generate and interpret dendrograms for optimal clusters
Compare clustering results from different linkage methods

Ensemble Learning Methods: Random Forest and Boosting CO3

• Train Random Forest classifier; evaluate accuracy, precision,

9 recall
• Implement Gradient Boosting and XGBoost; tune hyperparameters
• Compare training time, accuracy, overfitting tendencies
Visualize feature importance

Bayesian Classification: Naïve Bayes and Bayesian Networks CO3

• Implement Gaussian, Multinomial, and Bernoulli Naïve Bayes
classifiers
10 • Evaluate performance with classification metrics
• Hyperparameter tuning and feature selection
Introduce Bayesian Belief Networks with small datasets or predefined
structures