Fall 2024 CS Course Listings

This file contains the Fall 2024 course listings for the Department of Computer Science and Engineering.

Archive of past courses

Course code: COMP 5211
Course title: Advanced Artificial Intelligence
Instructor: Prof. Fangzhen Lin
Office: 3557
Telephone: 2358-6975
Email:
WWW Page: https://cse.hkust.edu.hk/~flin/

Area in which course can be counted: Artificial Intelligence (AI)

Course description:
This advanced AI course will cover the main concepts and techniques in AI. The major topics will be: AI agents, problem solving, machine learning, knowledge and reasoning, uncertain knowledge and reasoning.

Course objective:
Students are expected to gain deep understanding of key concepts and techniques in AI, including heuristic search strategies for single agent problem solving as well as multi-agent strategic planning such as in game playing, knowledge representation and reasoning using both logic and probabilities, machine learning, and integrated agent design.

Course outline/content (by major topics):
1. Introduction.
2. Agents: production systems, learning with perceptrons (linear networks), and genetic programming.
3. Game theory.
4. AI search.
5. Knowledge representation and reasoning: logic and belief networks.
6. Machine learning.

Textbooks:
Stuart Russell and Peter Norvig. Artificial Intelligence: A Modern Approach Prentice Hall, 2003.

Reference books/materials:
NIL

Grading scheme:

Available for final year UG students to enroll: Yes

Minimum CGA required for UG students: Permission of the instructor

Course code: COMP 5212
Course title: Machine Learning
Instructor: Dr. Junxian He
Office: 3512
Telephone: 2358-8765
Email:
WWW Page: https://jxhe.github.io/teaching/comp5212f24

Area in which course can be counted: Artificial Intelligence (AI)

Course description:
This course covers core and recent machine learning algorithms. Topics include supervised learning algorithms (linear regression, logistic regression, generative models for classification, support vector machines), unsupervised learning (K-Means, mixture models, latent-variable models, expectation maximization), deep learning, deep generative models, and reinforcement learning (classic RL, deep RL). The course assumes students have a solid grasp of probabilities, linear algebra, and python programming. This course is math-intensive, assignments and final projects will require proficient probability/linear algebra foundations and programming skills.

Background:
Computer science: object-oriented programming and data structures, design and analysis of algorithms; Mathematics: multivariable calculus, linear algebra and matrix analysis, probability and statistics.

Course objective:
Upon successful completion of the proposed course, students will be able to:
* Gain an overview of Machine Learning as a subject of study;
* Gain an understanding of the fundamental issues and principles in machine learning;
* Gain an understanding of core and recent machine learning algorithms;
* Gain an ability to apply core and recent machine learning algorithms to solve real-world problems.

Course outline/content (by major topics):
You may refer to https://jxhe.github.io/teaching/comp5212s24 for an example of covered topics.

Reference books/materials:
o Andrew Ng. Lecture Notes on Machine Learning. Stanford. https://cs229.stanford.edu/syllabus.html
o I Goodfellow, Y Bengio, A Courville (2016). Deep Learning. MIT Press. https://www.deeplearningbook.org/

Workload and Grading:
o 4 Normal Assignments + 1 Programming Project: (50%)
o Attendance: (10%)
o Mid-term Examination: (20%)
o Final Examination: (20%)

Available for final year UG students to enroll: PG students have higher priority to enroll in this course. UG students will be considered only if there are spare quota.

Minimum CGA required for UG students: 3.6

Course code: COMP 5331
Course title: Knowledge Discovery in Databases
Instructor: Prof. Raymond Wong
Office: 3541
Telephone: 2358-6982
Email:
WWW Page: http://cse.hkust.edu.hk/~raywong/

Area in which course can be counted: Data, Knowledge and Information Management (DB) or Artificial Intelligence (AI)

Course description:
Data mining has emerged as a major frontier field of study in recent years. Aimed at extracting useful and interesting patterns and knowledge from large data repositories such as databases and the Web, the field of data mining integrates techniques from database, statistics and artificial intelligence. This course will provide a broad overview of the field, preparing the students with the ability to conduct research in the field.

Background: COMP 3711

Course objective:
To learn the techniques used in data mining research. To help the students get ready for research.

Course outline/content (by major topics):
1. Classification.
2. Clustering.
3. Association.
4. Data Warehouse.
5. Data Mining over Data Streams.
6. Graph Databases.

Textbooks:
Data Mining: Concepts and Techniques. Jiawei Han, Micheline Kamber and Jian Pei. Morgan Kaufmann Publishers (4th edition).

Reference books/materials:
Introduction to Data Mining. Pang-Ning Tan, Michael Steinbach, Vipin Kumar Boston. Pearson Addison Wesley (2019).

Grading scheme:
Assignment 30%
Project 30%
Final Exam 40%

Available for final year UG students to enroll: Yes but with approval.

Minimum CGA required for UG students: 3.7

Course code: COMP 5621
Course title: Computer Networks
Instructor: Dr. Brahim Bensaou
Office: 3537
Telephone: 2358-7014
Email:
WWW Page: https://cse.hkust.edu.hk/~csbb/

Area in which course can be counted: Networking and Computer Systems (NE)

Course description:
Principles, design and implementation of computer communication networks; network architecture and protocols, OSI reference model and TCP/IP networking architecture; Internet applications and requirements; transport protocols, TCP and UDP; network layer protocols, IP, routing, multicasting and broadcasting; local area networks; data link and physical layer issues; wireless and mobile networking, multimedia networking.

Exclusion: COMP 4621

Course objective:
Upon completion of this course you will have an in depth knowledge about the foundations of current Internet applications, serviced and architecture and will learn about some of the challenges that are defining the future trends in the design of new services and protocols for the Internet.

Course outline/content (by major topics):

Textbooks:
* James Kurose and Keith Ross, Computer Networking: A Top Down Approach, (6th Ed.), Pearson, 2009.
* A collection of papers and articles provided as a reading list.

Reference books/materials:
NIL

Grading scheme:
Homework, paper presentation, and Final Exam.

Available for final year UG students to enroll: Yes

Minimum CGA required for UG students: Instructor Permission required

Course code: COMP 5711
Course title: Introduction to Advanced Algorithmic Techniques
Instructor: Prof. Ke Yi
Room: CYT-3002
Telephone: 2358-8770
Email:
WWW Page: https://cse.hkust.edu.hk/~yike/

Area in which course can be counted: Theoretical Computer Science (TH)

Course description:
This is an introductory graduate course in algorithmic techniques.

Background: COMP 3711, Discrete Mathematics, Probability

Course objective:
To equip students with a broad knowledge of general techniques for designing and analyzing algorithms.

Course outline/content (by major topics):
* Fixed-parameter algorithms
* Amortized analysis
* Randomized algorithms
* Hashing
* Tail inequalities and random sampling
* Online algorithms
* Streaming algorithms
* Parallel and distributed algorithms

Textbooks:
NIL

Reference books/materials:
* Introduction to Algorithms (3rd Edition). T. Cormen, C. Leiserson, R. Rivest, C. Stein. McGraw Hill and MIT Press.
* Randomized Algorithms. Rajeev Motwani, Prabhakar Raghavan, Cambridge University Press, 1995.
* Algorithm Design. Jon Kleinberg and Eva Tardos, Addison Wesley, 2005.

Grading scheme:
Assignments: 10%
Midterm exam: 30%
Final exam: 60%

Available for final year UG students to enroll: Yes

Minimum CGA required for UG students: A- and Permission of the instructor.

Course code: COMP 6211J
Course title: Advanced Large-Scale Machine Learning Systems for Foundation Models
Instructor: Dr. Binhang Yuan
Office: 3517
Telephone: 6978
Email:
WWW Page: https://github.com/Relaxed-System-Lab/COMP6211J_Course_HKUST

Area in which course can be counted: Artificial Intelligence (AI)

Course description:
In recent years, foundation models have fundamentally revolutionized the state-of-the-art of artificial intelligence. Thus, the computation in the training or inference of the foundation model could be one of the most important workflows running on top of modern computer systems. This course unravels the secrets of the efficient deployment of such workflows from the system perspective. Specifically, we will i) explain how a modern machine learning system (i.e., PyTorch) works; ii) understand the performance bottleneck of machine learning computation over modern hardware (e.g., Nvidia GPUs); iii) discuss four main parallel strategies in foundation model training (data-, pipeline-, tensor model-, optimizer- parallelism); and iv) real-world deployment of foundation model including efficient inference and fine-tuning.

Exclusion(s): Only PG students from CSE and ECE are expected to take the course.

Course objective:
o Be able to illustrate basic concepts and principles in foundation models.
o Be able to describe main parallel training strategies for distributed training and inference.
o Be able to understand the system bottleneck of computations relevant to foundation models.
o Be able to deploy some foundation model workflow for PG-level research work.

Course outline/content (by major topics):
o Gradient Descent Algorithms & Automatic Differentiation
o Nvidia GPU Computation and Communication
o Large-Scale Pretrain Overview
o Data Parallel Training & Pipeline Parallel Training
o Tensor Model Parallel Training & Optimizer Parallel Training
o Sequence Parallel Training & Mixture of Expert Parallel Training
o Generative Inference Overview
o Disaggregation and Low-precision Compression for Latency-oriented Inference
o Batching and Offloading for Throughput-oriented Inference
o Student Presentations

Textbooks:
N/A

Reference books/materials: Course Website

Grading scheme: Literature Review Report + Presentation + Research Plan

Available for final year UG students to enroll: Not allowed

Minimum CGA required for UG students: N/A

Please visit Class Schedule & Quota (Fall 2024) for the timetable and quota.

Archive of past courses

Last modified on 2024-09-05.