Course Description
This course provides a comprehensive introduction to machine learning, covering fundamental algorithms and techniques from linear methods to deep learning. Students will gain hands-on experience implementing machine learning algorithms in Python and applying them to real-world problems. The course emphasizes both theoretical understanding and practical application, preparing students to use machine learning effectively in their future work.
Key Topics Include:
- Data Analysis and Visualization: matplotlib, pandas, numpy
- Linear regression, Logistic Regression, Generalized Linear Models
- Generative learning and kernel methods: Support Vector Machines, Naive Bayes, Gaussian Discriminant Analysis
- Neural networks and deep learning: Fully connected, convolutional, and recurrent neural networks
- Unsupervised learning and dimensionality reduction: PCA, K-means, Gaussian Mixture Models
- Reinforcement learning: Markov Decision Processes, Q-learning, Policy Gradients
- Foundation models and language modeling: Transformers, LLMs, and self-supervised learning
- Ethics and future of machine learning: Bias, fairness, and responsible use of AI
Instructor
Joseph Bakarji
Email: jb50@aub.edu.lb
Office Hours: Thursday 1:30-3:30PM (or by appointment)
Office: Bechtel 418
Teaching Assistants
Ghina Daoud
Email: gad08@mail.aub.edu
Office Hours: TBA
Office: TBA
Shafik Houeidi
Email: sah89@mail.aub.edu
Office Hours: TBA
Office: TBA
Course Information
Prerequisites:
- Linear algebra (vectors, matrices, eigenvalues)
- Calculus (derivatives, chain rule, gradients)
- Probability and statistics basics
- Programming experience (Python preferred)
Format:
- Lectures: 2 sessions per week (75 minutes each)
- Labs: Hands-on programming sessions typically during lectures with occasional solving sessions
Assessment
| Component | Weight | Description |
|---|---|---|
| Project | 40% | Group ML project, in five deliverables |
| Assignments | 20% | 7-9 assignments |
| Final Exam | 15% | Date: TBD |
| Midterm | 10% | Date (tentative): Nov 5 |
| Quizzes | 10% | Short conceptual assessments |
| Participation | 5% | Class engagement, labs, and Slack |
The project’s 40% breaks down as pre-proposal 3%, proposal 7%, progress report 5%, poster session 10%, and final report 15%.
Recommended References:
- CS229 Lecture Notes from Stanford
- Hastie, Tibshirani, and Friedman. The Elements of Statistical Learning (free online)
- Murphy, K. P. Probabilistic Machine Learning: An Introduction (free online)
Important Policies
Academic Integrity
All work must be your own. Collaboration is encouraged for understanding concepts, but assignments must be completed individually unless explicitly stated otherwise.
Late Policy
Late assignments will be penalized 10% per day. Extensions may be granted for documented emergencies. Students are given 5 (emergency) extra days to use on any assignment (except project) submission.
Quick Links
- Schedule - Detailed course schedule with lecture topics and assignments
- Assignments - Programming assignments and projects
- Resources - Textbooks, datasets, and supplementary materials
- Logistics - Policies, grading, and course procedures
This website is continuously updated throughout the semester. Check back regularly for announcements and new materials.