Machine Learning (ES-442) - Lecture Slides

Instructor: Asif Ahmad
Institution: Faculty of Engineering Sciences, GIK Institute
Semester: Fall 2025

📘 Course Overview

This repository contains the complete lecture slides and course materials for Machine Learning (ES-442). The course provides a comprehensive introduction to the field of machine learning, covering the theoretical foundations and practical algorithms of the three main learning paradigms: Supervised Learning, Unsupervised Learning, and Reinforcement Learning.

Learning Objectives

By the end of this course, students will be able to:

• Understand the core concepts and theoretical foundations of machine learning
• Implement and analyze a wide range of ML algorithms
• Apply these algorithms to solve real-world problems of moderate complexity
• Evaluate and compare different learning approaches

📂 Repository Structure

Lectures-Slides/
├── 01-Intro-to-ML/                    # Introduction and Concept Learning
├── 02-Supervised-Learning/            # Classification, Regression, Neural Networks
├── 03-Unsupervised-Learning/          # Clustering, Dimensionality Reduction
└── 04-Re-Inforcement-Learning/       # MDPs, Q-Learning, Deep RL

📚 Lecture Materials

Module 1: Introduction to Machine Learning

Lecture	Topic	File
1-6	Introduction to ML, Concept Learning, Version Spaces, Candidate-Elimination Algorithm	Lecture-01-06-Introduction-to-ML(ML-ConceptLearning-VersionSpaces-CEA).pdf

Module 2: Supervised Learning

Lecture	Topic	File
7-9	Decision Trees, Overfitting, Pruning, Noisy Data	Lecture-07-09-Supervised-Learning-I-(Decision-Tree-And-Overfitting-Pruning-NoisyData).pdf
10	Naive Bayes Classifier	Lecture-10-Supervised-Learning-II-(Naive Bayes).pdf
11-12	Support Vector Machines (SVM)	Lecture-11-12-Supervised-Learning-III-(Support Vector Machine (SVM)).pdf
13	Linear Regression	Lecture-13-Supervised-Learning-IV-(Linear Regression).pdf
14	Logistic Regression	Lecture-14-Supervised-Learning-V-(Logistic Regression).pdf
15	Artificial Neural Networks: The Perceptron	Lecture-15-Supervised-Learning-VI-(ANN-The-Perceptron).pdf
16	ANN: Multi-Layer Perceptron and Backpropagation	Lecture-16-Supervised-Learning-VII-(ANN-The-MultiLayer-Perceptron-And-Backpropagation).pdf
17	ANN: Backpropagation in Action (XOR Problem)	Lecture-17-Supervised-Learning-VIII-(ANN-BackPropagation-In-Action-(XOR Problem)).pdf
18	ANN: Training in Practice	Lecture-18-Supervised-Learning-IX-(ANN-Training-In-Practice).pdf
19-20	ANN: Regularizations and Summary	Lecture-19-20-Supervised-Learning-X-(ANN-Regularizations-And-Summary).pdf

Module 3: Unsupervised Learning

Lecture	Topic	File
21	Hierarchical Agglomerative Clustering (HAC)	Lecture-21-Unsupervised-Learning-I-Hierarchical-Agglomerative-Clustering-(HAC).pdf
22	K-Means Partitional Clustering	Lecture-22-Unsupervised-Learning-II-K-Means-Partitional-Clustering.pdf
23	Self-Organizing Maps (SOM)	Lecture-23-Unsupervised-Learning-III-Self-Organizing-Maps-(SOM).pdf
24	Semi-Supervised Learning & The EM Algorithm	Lecture-24-Semi-Supervised Learning-&-The-EM-Algorithm.pdf

Module 4: Reinforcement Learning

Lecture	Topic	File
25	Introduction to Reinforcement Learning	Lecture-25-Re-Inforcement-Learning-I-Introduction-to-RL.pdf
26	Markov Decision Processes (MDPs)	Lecture-26-Re-Inforcement-Learning-II-Markov-Decision-Processes.pdf
27	Bellman Equations and Dynamic Programming	Lecture-27-Re-Inforcement-Learning-III-Bellman-Equations-And-DP.pdf
28	Monte Carlo Methods	Lecture-28-Re-Inforcement-Learning-IV-Monte-Carlo-Methods.pdf
29	Temporal Difference (TD) Learning	Lecture-29-Re-Inforcement-Learning-V-Temporal-Difference-(TD)-Learning.pdf
30	SARSA: On-Policy Control	Lecture-30-Re-Inforcement-Learning-VI-SARSA-On-Policy-Control.pdf
31	Q-Learning: Off-Policy Control	Lecture-31-Re-Inforcement-Learning-VII-Q-Learning-Off-Policy-Control.pdf
32	Exploration Strategies	Lecture-32-Re-Inforcement-Learning-VIII-Exploration-Strategies.pdf
33	Function Approximation	Lecture-33-Re-Inforcement-Learning-IX-Function-Approximation.pdf
34	Deep Reinforcement Learning (DQN)	Lecture-34-Re-Inforcement-Learning-X-Deep-Reinforcement-Learning-(DQN).pdf
35	Policy Gradient Methods: REINFORCE and Actor-Critic	Lecture-35-Re-Inforcement-Learning-XI-Policy-Gradient-Methods-REINFORCE-And-Actor-Critic.pdf
36	Case Studies and Applications	Lecture-36-Re-Inforcement-Learning-XII-Case-Studies-And-Applications.pdf

🛠 Prerequisites

To get the most out of this course, students should have:

• Statistics: Basic probability theory, distributions, and statistical inference
• Calculus: Derivatives, gradients, optimization techniques
• Linear Algebra: Vectors, matrices, matrix operations
• Programming: Proficiency in Python (NumPy, Pandas, Scikit-Learn, Matplotlib)

📝 Course Assessment

• Assignments: 5 total assignments covering all modules
• Quizzes: Periodic assessments throughout the semester
• Final Exam: Comprehensive practical exam covering Supervised, Unsupervised, and Reinforcement Learning

Note: Quizzes, Assignments, and other materials are distributed via the virtual class in Microsoft Teams.

📖 Textbooks

Text Books:

1. Machine Learning, Tom, M., McGraw Hill, 1997.
2. "Reinforcement Learning: An Introduction" by Sutton and Barto, Second Edition 2015.

Reference Books:

1. Machine Learning: A Probabilistic Perspective, Kevin P. Murphy, MIT Press, 2012.
2. Introduction to Machine Learning with Python, Andreas C. Müller and Sarah Guido, 2016.

📄 License

This content is provided for educational purposes. Please credit the original instructor if you adapt these materials.

---

Last Updated: Fall 2025