This repository contains all course materials, resources, and implementations for CSE-804: Machine Learning, a graduate-level course in the MS program at the College of Electrical and Mechanical Engineering (CEME), National University of Sciences and Technology (NUST).
"Machine intelligence is the last invention that humanity will ever need to make." — Nick Bostrom
| Department | Computer Engineering |
| College | College of Electrical and Mechanical Engineering (CEME) |
| University | National University of Sciences and Technology (NUST) |
| Semester | 1st Semester |
| Course Title | CSE-871 Machine Learning |
| Credit Hours | 3 |
| Instructor | Dr. Ali Hassan |
| Course Type | Core Lecture |
| Prerequisites | Basic knowledge of Linear Algebra, Partial Derivatives, and Matlab/Python |
| Program | MS Program |
| Instructor | Dr. Ali Hassan |
| Office | DCE-17 |
| alihassan@ceme.nust.edu.pk | |
| Consulting Hours | TUE Before Class or Email |
| Lecture Days | Tuesday |
| Classroom | CRC-11 |
| Component | Weightage | Badge |
|---|---|---|
| Midterm Exam | 30% |  |
| Final Exam | 40% |  |
| Assignments (4-6) | 10% |  |
| Quizzes (4-6) | 10% |  |
| Project | 10% |  |
- Quizzes will be unannounced and last 5-10 minutes
- Tests concepts from recent lectures
- Grading scale: 0-5 points
- 5: Exceptional attempt
- 4: Very good attempt
- 3: Good attempt
- 2: Satisfactory attempt
- 1: Poor attempt (but reasonable effort)
- 0: No reasonable effort
- Late assignments will not be accepted/graded
- All assignments count toward final grade
- Questions designed to be challenging for comprehensive understanding
- Zero tolerance for copying - violations referred to disciplinary committee
Plagiarism Policy: NUST CEME maintains zero tolerance towards plagiarism. Presenting others' work, ideas, theories, or code as your own will lead to strict penalties including zero marks and disciplinary action.
This course introduces graduate students to active research areas in Machine Learning, focusing on:
- 🧮 Understanding mathematical foundations of machine learning tools and pattern recognition systems
- 📊 Implementing and analyzing various ML algorithms from linear models to deep learning
- 🔧 Applying optimization techniques including Gradient Descent and Lagrange Multipliers
- 🎯 Developing proficiency in data handling, cross-validation, and dimensionality reduction
- 🤖 Exploring advanced topics like neural networks, SVMs, ensemble methods, and big data applications
| Week | Topics | Assessments |
|---|---|---|
| 1 | Introduction to the Course • Course overview • Topics coverage | |
| 2 | Pattern Recognition Fundamentals • Types of PR • PR system design cycle • Supervised vs Unsupervised Learning • Mathematics and calculus background | |
| 3 | Linear Regression Basics • Linear Regression with One Variable • Gradient Descent | |
| 4 | Advanced Linear Regression • Linear Regression with Multiple Variables • Polynomial Regression • Normal Equations | |
| 5 | Regularization • Linear Regression Regularization • Logistic Regression Regularization | |
| 6 | Neural Networks Introduction • Neural Networks Overview • Cost Function • Cost Function Minimization • No Back Propagation | |
| 7 | Model Evaluation • Pre-Processing • Generalization Error | |
| 8 | Feature Engineering • Multi-class Classification • Feature Selection • Dimensionality Reduction | MID TERM EXAM |
| 9 | Unsupervised Learning • Clustering • K-means Clustering • DBSCAN • AutoEncoders | |
| 10 | Texture Recognition • Texture Recognition • Local Binary Patterns • Homogeneous Texture | |
| 11 | Support Vector Machines I • Linear SVMs | |
| 12 | Support Vector Machines II • Separable/Non-Separable Linear • Separable/Non-Separable Non-Linear • Kernel Trick | |
| 13 | Ensemble Methods • Combining Classifiers • Bagging • Boosting • Ada-Boosting | |
| 14 | Genetic Algorithms • Genetic Algorithms Fundamentals | |
| 15 | Deep Learning • Deep Learning Introduction | |
| 16 | Recommender Systems • Collaborative Filtering for Recommender Systems (2 lectures) | |
| 17 | Big Data Applications • Machine Learning in Big Data | FINAL EXAM |
- "Machine Learning: A Probabilistic Perspective" by Kevin Murphy (Primary Textbook)
- "Pattern Classification" by Richard Duda, Peter Hart, and David Stork (2nd Edition)
- "Pattern Recognition and Machine Learning" by Christopher Bishop
- Lecture Notes (Provided in class)
- Online Material (Shared during lectures)
- Research Papers (For advanced topics)
- Python (Primary programming language)
- Basic knowledge of Matlab (optional)
NUST_MS_ML_CSE804/
│
├── 📂 Lectures/ # Slides and lecture notes
│ ├── Week_1_Introduction/
│ ├── Week_2_Pattern_Recognition/
│ └── .../
├── 📂 Assignments/ # Problem statements and solutions
│ ├── Assignment_1/ # First assignment
│ ├── Assignment_2/ # Second assignment
│ ├── Assignment_3/ # Third assignment
│ ├── Assignment_4/ # Fourth assignment
│ ├── Assignment_5/ # Fifth assignment
│ └── Assignment_6/ # Sixth assignment
├── 📂 Project/ # Semester project materials
│ ├── Proposal/ # Project proposal
│ ├── Implementation/ # Code and implementations
│ ├── Report/ # Final project report
│ └── Presentation/ # Project presentation slides
├── 📂 Code/ # Algorithm implementations
│ ├── Python/ # Python implementations
│ ├── Jupyter_Notebooks/ # Interactive notebooks
│ ├── Linear_Regression/ # Regression algorithms
│ ├── Neural_Networks/ # NN implementations
│ ├── SVM/ # Support Vector Machines
│ └── Unsupervised_Learning/ # Clustering algorithms
├── 📂 Resources/ # Additional learning materials
│ ├── Papers/ # Research papers
│ ├── Cheatsheets/ # Quick reference guides
│ ├── Datasets/ # Practice datasets
│ └── Tutorials/ # Step-by-step tutorials
└── 📂 Exams/ # Preparation materials
├── Midterm/ # Midterm exam resources
└── Final/ # Final exam resources
-
Clone the repository:
git clone https://github.com/your-username/NUST_MS_ML_CSE804.git
-
Navigate through weekly folders to follow the course progression
-
Complete assignments in the respective folders with proper documentation
-
Explore code implementations to understand algorithm workings
-
Check regularly for updates and additional resources
- Blockchain applications in machine learning
- Recommender Systems advanced techniques
- Advanced Unsupervised Learning methods
- Model Deployment and MLOps
- Ethical AI and responsible machine learning
- Course Instructor: Dr. Ali Hassan
- MS Program Students
- Teaching Assistants (if any)
This repository is for educational purposes for the students of MS Program, CEME-NUST. Please respect the academic integrity policy of the institution.
