Machine Learning
COMP 4211
The Hong Kong University of Science and Technology
Newt Nguyen
Course description: This course provides a comprehensive coverage of the machine learning field. There are 2 parts of this course: technical part and theoretical part. For the technical part, it will introduce necessary Python frameworks and OOP-related concepts for machine learning programming. For the theoretical part, it covers traditional machine learning and newly-emergent topics in large language models, computer vision, natural language processing, and some selected advanced topics.
Time and Location
Lectures: TBD
Some Reference books (will be updated as we go)
Participants should be comfortable with probability, linear algebra, and programming in Python. Helpful references:
Lecture Schedule
Schedules are tentative and subject to change. Slides will be posted here when available.
Technical Part 1 (programming & frameworks)
Python, OOP, and tooling for machine learning implementation.
| Slides | Date | Topic | Readings | Assignments |
|---|---|---|---|---|
| COMP 2211 Python Basics Extra NumPy | Week 1 | Matrix Programming Basics | ||
| Project 1 | Week 1-2 | Project 1 | ||
| Pandas | Week 2 | Pandas | ||
| OOP for Python | Week 2 | OOP for Python | ||
| Scikit-Learn Project | Week 2 7th June 2026 | Scikit-Learn Project | ||
| K Nearest Neighbors | Week 2 | K Nearest Neighbors | ||
| K Means Clustering | Week 2 | K Means Clustering | ||
| Project 2 | Week 2 | Project 2 | ||
| Week 2 | Introduction to Keras | |||
| Week 3 | Introduction to PyTorch | |||
| Week 4 | Introduction to Hugging Face |
Theoretical Part 1 (ML concepts & applications)
Foundations, classical algorithms, and selected modern topics (LLM, CV, NLP).
| Slides | Date | Topic | Readings | Assignments |
|---|---|---|---|---|
| Introduction | CS229 Notes | |||
| Linear Regression Written Notes Video Link | 7th June 2026 | Linear Regression | ||
| Logistic Regression | Logistic Regression | |||
| Feedforward Neural Networks | Feedforward Neural Networks | |||
| Deep Neural Networks | Deep Neural Networks | |||
| Stochastic Gradient Descent | ||||
| Automatic Differentiation | ||||
| Convolutional Neural Networks | ||||
| Recurrent Neural Networks | ||||
| Autoencoders | ||||
| Reinforcement Learning |
Theoretical Part 2 (LLM & GPU Performance)
| Slides | Date | Topic | Readings | Assignments |
|---|---|---|---|---|
| Language Models Architecture | ||||
| LLM Pretraining | ||||
| Nvidia GPU Performance | ||||
| Nvidia Collective Communication Library | ||||
| Data and Pipeline Parallel Training | ||||
| Tensor Parallelism and ZeRO Optimizer | ||||
| Mixture-of-Experts and Sequence Parallelism | ||||
| Generative Inference Overview |
Theoretical Part 3 (Computer Vision)
| Slides | Date | Topic | Readings | Assignments |
|---|---|---|---|---|
| Linear Classifier | Image Classification with Linear Classifier |
Paper Discussion (will update as we go)
| Paper Link | Paper Name | Topic |
|---|---|---|
| Nielsen et al. (2026) | Learning to Orchestrate Agents in Natural Language with the Conductor | LLM Conductors |
| Wang et al. (2024) | Mixture-of-Agents Enhance Large Language Model Capabilities | LLM Conductors |
| Yue et al. (2025) | MasRouter: Learning to Route LLM for Multi-Agent System | LLM Conductors |
| Madaan et al. (2023) | Self-Refine: Iterative Refinement with Self-Feedback | LLM Conductors |
| Du et al. (2023) | Improving Factuality and Reasoning in Language Models through Multiagent Debate | LLM Conductors |
| Zheng et al. (2025) | Survey on LLM for Scientific Discovery | LLM for Scientific Discovery |
| Jiang et al. (2025) | AIDE: AI-Driven Exploration in the Space of Code | AI4AI LLM Reasoning |
| Liu et al. (2025) | ML-Master | AI4AI LLM Reasoning |
| Zhu et al. (2026) | ML-Master 2.0 | AI4AI LLM Reasoning |
| Dosovitskiy et al. (2021) | An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale | Computer Vision |
| Li et al. (2025) | WebSailor | AI Research Agent |