 |
| PRE-REQUISITE | UFUG 2103 OR UFUG 2102 |
|---|---|
| DESCRIPTION | This course will introduce topics in probability and statistics. Topics include probability spaces and random variables, distributions (absolutely continuous and singular distributions) and probability densities, moment inequalities, moment generating functions, conditional expectations, independence, conditional distributions, convergence concepts (weak, strong and in distribution), law of large numbers (weak and strong) and central limit theorem. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6439) | Mo 01:30PM - 03:20PM | Rm 102, W1 | SUN, Jianfeng | 40 Quota/Enrol/Avail SMMG UG students: 13/0/13 | 0 | 40 | 0 | |
| Fr 09:00AM - 10:50AM | Rm 102, W1 | SUN, Jianfeng |
| PRE-REQUISITE | (DSAA 1001 or AIAA 2205) OR (FTEC 3130 for FTEC Major Only) |
|---|---|
| DESCRIPTION | Machine learning is an exciting and fast-growing field that leverages data to build models which can make predictions or decisions. This is an introductory machine learning course that covers fundamental topics in model assessment and selection, supervised learning (e.g., linear regression, logistic regression, neural networks, deep learning, support vector machines, Bayes classifiers, decision trees, ensemble methods); unsupervised learning (e.g., clustering, dimensionality reduction); and reinforcement learning. Students will also gain practical programming skills in machine learning to tackle real-world problems. Basic knowledge on mathematics (e.g., basic of probability theory, linear algebra, calculus and optimization), programming (e.g., Python / C++ / Matlab) and data science are essential and will benefit the study of this course. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6435) | Th 09:00AM - 11:50AM | Rm 134, E1 | YANG, Weikai ZHONG, Zixin | 70 | 0 | 70 | 0 | |
| L02 (6436) | Mo 09:00AM - 11:50AM | Rm 122, E1 | YANG, Weikai ZHONG, Zixin | 70 | 0 | 70 | 0 | |
| LA01 (6437) | Th 07:00PM - 07:50PM | Rm 122, E1 | YANG, Weikai ZHONG, Zixin | 70 | 0 | 70 | 0 | |
| LA02 (6438) | Th 06:00PM - 06:50PM | Rm 122, E1 | YANG, Weikai ZHONG, Zixin | 70 | 0 | 70 | 0 |
| PRE-REQUISITE | DSAA 2011 or AIAA 3111 |
|---|---|
| DESCRIPTION | This course provides students with an extensive exposure to deep learning. Topics include shallow and deep neural networks, activation functions and rectified linear unit, construction of deep neural networks and matrix representations including deep convolutional neural networks and deep recursive neural networks, computational issues including backpropagation, automatic differentiation, stochastic gradient descent, complexity analysis, approximation analysis including universality of approximation, design of deep neural network architectures and programming according to various applications. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6440) | Tu 09:00AM - 11:50AM | Rm 134, E1 | LIANG, Chen | 40 Quota/Enrol/Avail Year 3 UG Students: 40/0/40 | 0 | 40 | 0 | |
| LA01 (6441) | Tu 06:00PM - 06:50PM | Rm 134, E1 | LIANG, Chen | 40 | 0 | 40 | 0 |
| PRE-REQUISITE | DSAA 2043 |
|---|---|
| DESCRIPTION | Topics include: principles of database systems; conceptual modeling and data models; logical and physical database design; query languages and query processing; database services including concurrency, crash recovery, security and integrity. Hands-on DBMS experience. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6442) | MoWe 04:30PM - 05:50PM | Rm 148, E1 | TANG, Nan | 50 Quota/Enrol/Avail DSA UG: 21/0/21 | 0 | 50 | 0 | |
| LA01 (6443) | We 07:00PM - 07:50PM | Rm 228, E2 | TANG, Nan | 50 | 0 | 50 | 0 |
| PRE-REQUISITE | UFUG 2602 |
|---|---|
| DESCRIPTION | Design and Analysis of Algorithms is an important course that bridges students to a number of advanced courses in data science and analytics. This course introduces core data structures and algorithms. It covers advanced asymptotic complexity analysis, introduces common algorithmic paradigms (e.g., divide-and-conquer, greedy, and dynamic programming), a collection of classic algorithms (e.g., graph algorithms) and introduces the computational complexity theory. The course employs a range of assessment methods, including individual projects, coding exercises and closed-book exams, to foster both theoretical and practical foundation. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6444) | MoWe 03:00PM - 04:20PM | Rm 122, E1 | ZHANG, Yanlin | 48 | 0 | 48 | 0 | |
| LA01 (6445) | We 06:00PM - 06:50PM | Rm 227, E1 | ZHANG, Yanlin | 48 | 0 | 48 | 0 |
| PRE-REQUISITE | DSAA 2043 |
|---|---|
| DESCRIPTION | This course introduces advanced algorithmic techniques, including amortized analysis, randomized algorithms, and approximation algorithms. Students will learn about advanced data structures and their applications, as well as advanced solutions for optimization problems like linear programming and network flow. The course emphasizes the design and analysis of these techniques while also covering problem hardness and tractability, providing a solid foundation in advanced algorithms. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6415) | WeFr 01:30PM - 02:50PM | Rm 202, W4 | LU, Shangqi | 40 | 0 | 40 | 0 | |
| T01 (6416) | Fr 03:00PM - 03:50PM | Rm 227, E1 | LU, Shangqi | 40 | 0 | 40 | 0 |
| PRE-REQUISITE | DSAA 2012 |
|---|---|
| DESCRIPTION | Topics include history and motivations of reinforcement learning, tabular solution methods such as multi-arm bandits, finite Markov decision process, dynamic programming, monte carlo methods and temporal difference learning, approximate solution such as on-policy approximation of action values, and off-policy approximation. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6413) | Tu 03:00PM - 05:50PM | Room 521H VR Room, W1 | ZHONG, Zixin | 20 | 0 | 20 | 0 | |
| LA01 (6414) | Th 02:00PM - 02:50PM | Rm 228, E1 | ZHONG, Zixin | 20 | 0 | 20 | 0 |
| PRE-REQUISITE | UFUG 2106 OR DSAA 2088 OR DSAA 2043 |
|---|---|
| DESCRIPTION | This course is an introduction to the foundation of computing. Topics include set theory and countability, formal languages, finite automata and regular languages, pushdown automata and context-free languages, Turing machines, undecidability, P and NP, NP completeness, Approximate Algorithms, and Advanced algorithm Analysis. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6412) | Th 03:00PM - 05:50PM | Rm 102, W1 | LIU, Jinguo | 40 | 0 | 40 | 0 |
| PRE-REQUISITE | DSAA 2031 AND UFUG 1601 |
|---|---|
| CROSS CAMPUS COURSE EQUIVALENCE | COMP 4651 |
| DESCRIPTION | Big data systems, including Cloud Computing and parallel data processing frameworks, emerge as enabling technologies in managing and mining the massive amount of data across hundreds or even thousands of commodity servers in datacenters. This course exposes students to both the theory and hands-on experience of this new technology. The course will cover the following topics. (1) Basic concepts of Cloud Computing and production Cloud services; (2) MapReduce - the de facto datacenter-scale programming abstraction - and its open source implementation of Hadoop. (3) Apache Spark - a new generation parallel processing framework - and its infrastructure, programming model, cluster deployment, tuning and debugging, as well as a number of specialized data processing systems built on top of Spark. By walking through a number of hands-on labs and assignments, students are expected to gain first-hand experience programming on real world clusters in production datacenters. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6410) | Th 09:00AM - 11:50AM | Rm 102, W4 | TANG, Guoming | 40 | 0 | 40 | 0 | |
| LA01 (6411) | Fr 04:30PM - 05:20PM | Rm 150, E1 | TANG, Guoming | 40 | 0 | 40 | 0 |
| PRE-REQUISITE | DSAA 2011 OR DSAA 2012 OR AIAA 3111 |
|---|---|
| CROSS CAMPUS COURSE EQUIVALENCE | MATH 4335 |
| DESCRIPTION | This course introduces fundamental theory and techniques of optimization. Topics include linear programming, unconstrained optimization, and constrained optimization. Numerical implementations of optimization methods are also discussed. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6402) | Tu 12:00PM - 02:50PM | Rm 201, E1 | CUI, Ying | 40 | 0 | 40 | 0 | |
| T01 (6403) | Fr 07:30PM - 08:20PM | Rm 150, E1 | CUI, Ying | 40 | 0 | 40 | 0 |
| VECTOR | [3-0-0:3] |
|---|---|
| DESCRIPTION | In this course, theories, models, algorithms of deep learning and their application to data science will be introduced. The basics of machine learning will be reviewed at first, then some classical deep learning models will be discussed, including AlexNet, LeNet, CNN, RNN, LSTM, and Bert. In addition, some advanced deep learning techniques will also be studied, such as reinforcement learning, transfer learning and graph neural networks. Finally, end-to-end solutions to apply these techniques in data science applications will be discussed, including data preparation, data enhancement, data sampling and optimizing training and inference processes. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6234) | Tu 12:00PM - 02:50PM | Rm 102, E4 | XIA, Jun | 120 Quota/Enrol/Avail For PhD (DSA) students only: 50/0/50 | 0 | 120 | 0 |
| VECTOR | [3-0-0:3] |
|---|---|
| DESCRIPTION | In this course, advanced algorithms for data science will be introduced. It covers most of the classical advanced topics in algorithm design, as well as some recent algorithmic developments, in particular algorithms for data science and analytics. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6250) | Th 01:30PM - 04:20PM | Rm 228, E2 | CHU, Xiaowen | 50 | 0 | 50 | 0 |
| VECTOR | [3-0-0:3] |
|---|---|
| DESCRIPTION | This course introduces basic concepts and technologies of blockchain, such as the hash function and digital signature, as well as data analysis and privacy protection over blockchain applications. The students will learn the consensus protocols and algorithms, the incentives and politics of the block chain community, the mechanics of Bitcoin and Bitcoin mining, data analysis techniques over blockchain and user/transaction privacy protection. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6251) | Th 09:00AM - 11:50AM | Rm 228, E2 | TANG, Jing | 60 | 0 | 60 | 0 |
| VECTOR | [3-0-0:3] |
|---|---|
| DESCRIPTION | In this course, we will introduce spatial and multimedia database management concepts, theories and technologies, from data representation, indexing, fundamental operations to advanced query processing. Challenges and solution for high dimensional data will also be introduced. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6252) | Fr 01:30PM - 04:20PM | Rm 222, W1 | LI, Lei | 40 | 0 | 40 | 0 |
| VECTOR | [3-0-0:3] |
|---|---|
| PREVIOUS CODE | DSAA 6000B |
| DESCRIPTION | Graph, as a very expressive model, has been widely used to model real-world entities and their relationships in application-specific networks. In this course, students will gain a thorough introduction to the basics of graph theories, as well as cutting-edge research in deep learning for graphs. The topics include graph embeddings, graph neural networks, graph clustering models, graph generative models, adversarial attacks on graphs, graph reasoning, etc. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6299) | Tu 03:00PM - 05:50PM | Rm 134, E1 | ZHANG, Yongqi | 60 | 0 | 60 | 0 |
| VECTOR | [3-0-0:3] |
|---|---|
| DESCRIPTION | Large language model (LLM) based-Agents have been an important frontier in AI, however, they still fall short critical skills, such as complex reasoning, for solving hard problems and enabling applications in real-world scenarios. This course covers the foundations and applications of language agents that can continuously improve themselves through interaction with the environment. The course will start with inference and post-training techniques for building language agents, such as scaling test-time compute, combining tools with LLMs, and reinforcement learning with verified rewards, etc. We focus on two application domains: mathematics and programming. Our goal is that the students learn from the latest research papers, discuss the suggested readings in each class, work on an original research project in this area, and learn from invited academic and industry speakers about applications in building language agents. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6301) | We 04:30PM - 07:20PM | Rm 102, E1 | GUO, Zhijiang | 40 Quota/Enrol/Avail For PhD (DSA) students only: 20/0/20 | 0 | 40 | 0 |
| VECTOR | [3-0-0:3] |
|---|---|
| DESCRIPTION | Tables are a crucial component of data management and analysis, yet their potential is often underutilized. This project-driven course addresses this gap by equipping students with both theoretical knowledge and practical skills in table representation learning. The course is divided into four parts: (1) Theory: Core concepts of table representation learning, including tabular data analysis, representation learning, multimodal integration (with code and text), and retrieval-augmented generation (RAG). (2) Tools and Techniques: Exploration of advanced tools such as deep learning models, large language models (LLMs), multimodal LLMs, and RAG methods, with a focus on pre-training paradigms for table-related tasks. (3) Table Analysis Applications: Practical applications, including Natural language to SQL (NL2SQL), Table Question Answering (TableQA), Table Visualization, and Data storytelling, demonstrating the use of table representation learning in real-world scenarios. (4) Course Project: A solo project where students apply the concepts and tools learned to address a real-world problem related to table representation learning. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6448) | Mo 01:30PM - 04:20PM | Rm 147, E1 | LUO, Yuyu | 40 | 0 | 40 | 0 |
| VECTOR | [3-0-0:3] |
|---|---|
| DESCRIPTION | This course delves into the foundational theories and cutting-edge advancements in large language models (LLMs). The course emphasizes LLM's application in real-world scenarios, focusing on topics such as domain-specific LLMs (e.g., continuous pretraining, SFT, and RLHF), data-intensive and document-intensive scenarios (e.g., NL2SQL RAG). Active student participation is encouraged through mini-projects, presentations, and discussions, providing hands-on experience in leveraging LLMs for real-world challenges. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6449) | Mo 06:00PM - 08:50PM | Lecture Hall C | WEI, Jiaheng | 80 Quota/Enrol/Avail For PhD (DSA) students only: 40/0/40 | 0 | 80 | 0 |
| VECTOR | [3-0-0:3] |
|---|---|
| DESCRIPTION | This course provides a comprehensive introduction to the fundamental principles and practices of how data is transmitted, managed, and protected across modern computer networks. It examines the architecture, design, and operation of the Internet from the application to the network layer, articulating how data is encoded, routed, and delivered over distributed systems. We will also learn the mechanisms that ensure data remains confidential, authentic, and available as it moves through complex communication environments. By integrating principles of data communication with the foundations of network security, the course provides a coherent view of how the modern Internet support scalable, reliable and secure exchange of massive data in the digital age. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6303) | We 09:00AM - 11:50AM | Rm 102, E1 | DUAN, Huayi | 40 | 0 | 40 | 0 |
| VECTOR | [1 credit] |
|---|---|
| DESCRIPTION | This course offers students opportunities to learn the possible industry topics and supervisors that they will work with during their internship. The goals are: (a) understand (i) problems in industry, (ii) existing data-sets, (iii) AI models, (iv) service scenario and KPI, (v) challenges; (b) propose industrial projects based on the understanding; and (c) matching for their industrial projects. This course is only available for MSc(DCAI) students. Graded P or F. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6709) | TBA | No room required | TBA | 100 | 0 | 100 | 0 |
| VECTOR | [1-0-0:1] |
|---|---|
| DESCRIPTION | In this course, students are required to attend at least 6 seminars offered by the program. The program will offer at least 10 seminars related to the state-of-the-art research on data science and analytics in each term. These seminars will help students to broaden the horizons of their knowledge on data science and analytics. Graded P or F. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| L01 (6300) | Tu 11:00AM - 11:50AM | Rm 101, W1 | TANG, Nan | 150 | 0 | 150 | 0 |
| VECTOR | [6 credits] |
|---|---|
| DESCRIPTION | In this course, the student will work on a practical project. The independent project is related to real problems existing in data science and AI application domains. The student needs to conduct literature survey, method comparison, solution selection and implementation, experimental study and write the final report. The course will train students skills on proposing end-to-end solution for a realapplications problem. This course is only available for MSc(DCAI) students. Graded P or F. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| R01 (6710) | TBA | No room required | TBA | 100 | 0 | 100 | 0 |
| VECTOR | [3 credits] |
|---|---|
| PRE-REQUISITE | DSAA 6920 |
| DESCRIPTION | In this course, students will be trained in the industry. They will work under the guidance of their supervisors (industry and academia) to practice what they have learned in the program, and apply the data science and AI knowledge and techniques to various real-life problems. In Part II, students are required to complete an Intermediate report with oral examination on the student’s progress and industry collaboration progress. This course is only available for MSc(DCAI) students. Graded PP, P or F. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| R01 (6711) | TBA | No room required | TBA | 100 | 0 | 100 | 0 |
| VECTOR | [3 credits] |
|---|---|
| PRE-REQUISITE | DSAA 6920 and DSAA 6921 |
| DESCRIPTION | In this course, students will be trained in the industry. They will work under the guidance of their supervisors (industry and academia) to practice what they have learned in the program, and apply the data science and AI knowledge and techniques to various real-life problems. In Part III, students are required to complete a Final report with oral examination on the final output from the internship project and whether the student indeed knows how to apply AI techniques to concrete data science applications. This course is only available for MSc(DCAI) students. Graded PP, P or F. |
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| R01 (6712) | TBA | No room required | TBA | 100 | 0 | 100 | 0 |
| DESCRIPTION | Master's thesis research supervised by co-advisors from different disciplines. A successful defense of the thesis leads to the grade Pass. No course credit is assigned. |
|---|
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| R01 (6014) | TBA | No room required | TBA | 100 | 0 | 100 | 0 |
| DESCRIPTION | Original and independent doctoral thesis research supervised by co-advisors from different disciplines. A successful defense of the thesis leads to the grade Pass. No course credit is assigned. |
|---|
| Section | Date & Time | Room | Instructor | Quota | Enrol | Avail | Wait | Remarks |
|---|---|---|---|---|---|---|---|---|
| R01 (6016) | TBA | No room required | TBA | 100 | 0 | 100 | 0 |