Postgraduate Courses

Back

Expand All Print All

AIAA

Artificial Intelligence

AIAA 5023
Foundations of Deep Neural Networks
[3-0-0:3]
Description
This course helps students to get basic knowledge about deep neural networks, helping them to understand basic concepts, capabilities and challenges of deep neural networks.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate a general comprehension of fundamental knowledge in deep neural networks.
- 2.
  Demonstrate comprehension of modern research topics in deep neural networks.
- 3.
  Demonstrate comprehension of the application of deep neural networks.
- 4.
  Recognize the application scope of current methods in deep neural networks.
- 5.
  Demonstrate oral/writing skills in computer vision community.
AIAA 5024
Advanced Deep Learning
[3-0-0:3]
Description
This course covers recent developments in deep learning. Topics include meta learning, model compression, federated learning, representation learning, explainable AI, adversarial attack and defense, and advances in deep learning theory.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate a comprehension of advanced knowledge of deep learning.
- 2.
  Demonstrate a comprehension of Modern research topics in deep learning.
- 3.
  Demonstrate a comprehension of applications of deep learning methods.
- 4.
  Recognize the limitations of current methods and make improvements.
- 5.
  Apply programming and data analytic skills.
AIAA 5025
Deep Reinforcement Learning
[3-0-0:3]
Description
This course covers recent developments in deep reinforcement learning. Topics include reinforcement learning basics, deep Q-learning, policy gradients, actor-critic algorithms, model-based reinforcement learning, imitation learning, inverse reinforcement learning, hierarchical reinforcement learning, and multi-agent reinforcement learning.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate an understanding of deep reinforcement learning as a field of study.
- 2.
  Demonstrate an understanding of the fundamental issues and principles in deep reinforcement learning.
- 3.
  Demonstrate an understanding of core and recent deep reinforcement learning algorithms.
- 4.
  Apply core and recent deep reinforcement learning algorithms to solve real-world problems.
AIAA 5026
Computer Vision and Its Applications
[3-0-0:3]
Description
This course covers popular topics in computer vision, which includes high-level tasks like image classification, object detection, image segmentation, and low-level tasks like image generation, image enhancement, image-to-image translation, etc.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate a general comprehension of fundamental knowledge in computer vision.
- 2.
  Demonstrate comprehension of modern research topics in computer vision.
- 3.
  Demonstrate comprehension of computer vision applications.
- 4.
  Recognize the application scope of current methods.
- 5.
  Demonstrate skills in oral/writing in computer vision community.
AIAA 5027
Chasing Trends for Visual Intelligence: From Restoration to 3D Reconstruction
[3-0-0:3]
Background
Basic knowledge of vision/graphics and machine learning would be preferred.
Description
This is a task-oriented yet interaction-based course, which aims to scrutinize the recent trends and challenges in visual intelligence tasks (from the image restoration to 3D vision tasks). This course will follow the way of flipped-classroom manner where the lecturer teaches the basics; meanwhile, the students will also be focused on active discussions, presentations (lecturing), and hands-on research projects under the guidance of the lecturer in the whole semester. Through this course, students will be equipped with the capability to critically challenge the existing methodologies/techniques and hopefully make breakthroughs in some new research directions.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate a comprehensive understanding of the basics in computer vision.
- 2.
  Catch up with the recent trends of deep learning for computer vision.
- 3.
  Identify the challenges and potentials of computer vision.
- 4.
  Foster good ways of paper reading and problem findings in computer vision research.
- 5.
  Critically challenge existing methods and explore new ways in computer vision.
- 6.
  Motivate interests in new research directions in computer vision, such as event camera-based vision.
AIAA 5028
Machine Learning on Graphs
[3-0-0:3]
Background
Implement machine learning and deep learning codes in Python; Basic probability theory and linear algebra.
Description
This course covers recent developments in machine learning on graph-structured data. Topics include network embedding, graph neural networks, knowledge graph embedding, generative models for graphs, scalable graph neural networks, explainable graph neural networks, and their applications.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate a comprehension of advanced knowledge of machine learning on graphs.
- 2.
  Demonstrate a comprehension of modern research topics in machine learning on graphs.
- 3.
  Demonstrate a comprehension of applications of graph learning methods.
- 4.
  Recognize the limitations of current methods and make improvements.
- 5.
  Apply programming and data analytic skills.
AIAA 5029
Programming for Vision Systems
[3-0-0:3]
Description
This course is a hands-on introduction to the algorithms and programming for visual learning problems of the intelligent mobile systems, such as self-driving cars, in the era of industry 4.0. This course is highlighted by practical programming assignments and projects. This course will first introduce the basic principles of machine/deep learning and computer vision. Then, the specific visual learning tasks crucial for achieving intelligent mobile systems (e.g., object detection, semantic segmentation, optical flow, stereo/depth estimation, pose estimation, lane detection, traffic sign detection) will be covered. Finally, the latest development of novel sensor-based vision and AI-based augmented reality (AR) /metaverse technologies for intelligent mobile systems will also be introduced.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Clearly understand the basic principles and techniques for intelligent systems.
- 2.
  Master the fundamental programming skills for visual learning problems in intelligent systems.
- 3.
  Identify the challenges and potentials in visual learning of intelligent systems.
- 4.
  Lay a solid foundation for further research in visual learning of intelligent systems.
- 5.
  Master the skills of paper reading and problem findings for intelligent systems.
AIAA 5030
Foundations of Data Mining
[3-0-0:3]
Description
This course will introduce the fundamental principles, uses, and technical details of data mining techniques by lectures and real-world case studies. The emphasis is on understanding the basic data mining techniques and their applications. We will discuss the mechanics of how data analytics techniques work as is necessary to understand the fundamental concepts and real-world applications.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate a comprehensive understanding of the basics in data mining.
- 2.
  Catch up with the current trends of data mining.
- 3.
  Demonstrate a comprehension of applications of data mining.
- 4.
  Identify the limitations of current methods and explore the improvements.
- 5.
  Critically apply data mining for business intelligence.
AIAA 5031
Introduction to Computing Using Python
[3-0-0:3]
Background
Basic programming skills, basic probability theory, linear algebra, and machine learning knowledge.
Description
This course covers how to program with Python and use it to solve practical problems in Artificial Intelligence. Topics include basic Python usage (e.g., syntax, data structure, etc.) and important packages for data analysis and machine learning applications (e.g., NumPy, SciPy, etc.). The students will be guided to practice on simple artificial intelligence tasks.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Develop Python programs.
- 2.
  Apply Python for efficient mathematical calculation in scientific research.
- 3.
  Discover real-world phenomena and problems by processing and analyzing real-world data.
- 4.
  Develop AI models to address real-world applicational problems.
- 5.
  Comprehensively understand the use of scientific methods and techniques in AI.
AIAA 5032
Foundations of Artificial Intelligence
[3-0-0:3]
Background
Programming in Python; Basic probability theory and linear algebra; Discrete Math
Description
This course aims to provide students with an overview of Artificial Intelligence (AI) principles and techniques. Key topics include machine learning, search, game theories, Markov decision process, constraint satisfaction problems, Bayesian networks, etc. Through this course, students will learn and practice the foundational principles, techniques and tools to tackle new AI problems.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate a fundamental understanding of AI research and applications.
- 2.
  Understand the status of current AI research and applications, including their limitations and future potential.
- 3.
  Understand several common forms of inputs for AI research and applications.
- 4.
  Understand the core principles of AI research and experimental designs.
- 5.
  Demonstrate a comprehension of key algorithms and models in AI.
- 6.
  Design and develop small AI projects using the learned techniques.
AIAA 5033
AI Security and Privacy
[3-0-0:3]
Background
Basic knowledge of AI technologies, such as machine learning and federated learning; A bachelor’s degree in computer science or relevant disciplines.
Description
This course introduces potential security and privacy vulnerabilities in Artificial Intelligence (AI) and covers basic and advanced protections. Topics include security and privacy risks in AI technologies, the goal of C.I.A. (Confidentiality, Integrity and Availability) in AI technologies, basic and advanced cryptography, protocol designs for AI security and privacy, etc.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate a comprehension of security and privacy risks in AI technology.
- 2.
  Demonstrate a comprehension of data confidentiality protection technologies.
- 3.
  Demonstrate a comprehension of data integrity protection technologies.
- 4.
  Demonstrate a comprehension of availability ensuring technologies.
- 5.
  Recognize the limitations of current methods and make improvements.
AIAA 5034
Reinforcement Learning and Optimization
[3-0-0:3]
Background
Basic knowledge in machine learning, programming, and optimization.
Description
Learning to make good decisions is one of the keys to autonomous systems. This course will focus on Reinforcement Learning (RL), a currently very active subfield of artificial intelligence, and it will discuss selectively a number of algorithmic topics including Markov Decision Process, Q-Learning, function approximation, exploration and exploitation, policy search, imitation learning, model-based RL and optimal control. This course provides both the foundations and techniques for developing RL and deep RL algorithms that interact with physical environments, and real application cases of RL will be introduced. Basic knowledge of machine learning and mathematical optimization are expected for this course.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate fundamental understanding of reinforcement learning, such as Markov Decision Process, multi-armed bandits, Q-Learning, policy gradients, and imitation learning.
- 2.
  Address challenges in autonomous decision making by integrating scientific knowledge, technical applications, and innovative technology.
- 3.
  Identify and describe different scientific methods to critically evaluate complex, emerging decision-making problems for single agent and multi-agent scenarios.
- 4.
  Recognize the importance of exploration and exploitation to learn to make decisions under unknown environments.
- 5.
  Develop a broad interest in the environment and connect the knowledge to their major study.
- 6.
  Communicate effectively in written format and programming language to convey scientific knowledge and the application of machine learning techniques.
- 7.
  Apply the knowledge in solving engineering and technological challenges.
AIAA 5036
Embodied AI
[3-0-0:3]
Background
Programming in Python; Basic probability theory and linear algebra; Discrete Math
Description
This course aims to provide students with key principles and algorithms to build modern embodied AI systems. Key topics include machine perception, planning and decision-making algorithms. Through this course, students will learn and practice the foundational principles, techniques, and tools to build new embodied AI systems.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate a fundamental understanding of autonomous AI research and applications.
- 2.
  Understand the status of current autonomous AI research and applications, including their limitations and future potential.
- 3.
  Understand several common designs of autonomous AI systems.
- 4.
  Demonstrate a comprehension of key algorithms and models in autonomous AI.
- 5.
  Design and develop small AI projects using the learned techniques.
AIAA 5037
Advanced Algorithms and Data Structures
[3-0-0:3]
Background
Basic programming skills
Description
This course covers typical algorithms and data structures. Topics include core methodologies of algorithm design, standard data structures, and typical algorithms and data structures that have been widely adopted for solving different problems, covering from fundamental ones (e.g., searching and sorting algorithms) to more advanced ones (e.g., graph algorithms, number theory algorithms, FFT).
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate interest in designing more efficient algorithms to solve problems.
- 2.
  Understand typical fundamental and advanced algorithms.
- 3.
  Understand principles and usage of standard data structures.
- 4.
  Formulate real-world problems and design algorithms to solve them.
- 5.
  Know how to analyze the complexity of algorithms.
AIAA 5045
Artificial Intelligence for Medical Imaging
[3-0-0:3]
Background
Familiar to use Python for coding, and have fundamental knowledge of Machine Learning.
Description
This course will explore the basic knowledge and the latest advances of Deep Learning based methods in the medical field, with special attention to challenges and opportunities for Medical AI. This course will provide students the opportunity to learn skills to train/learn/develop Deep Learning models from medical data with several case studies. It covers knowledge on Digital Medical Imaging, supervised learning, semi-supervised learning, and unsupervised learning related with Medical AI research. Importantly, some hot topics on "AI for Medical" will be introduced.
AIAA 5046
Fundamentals of Machine Learning
[3-0-0:3]
Background
Students are expected to have knowledge of statistics, probability theory, linear algebra, and calculus.
Description
Machine learning is a cornerstone of AI. The course targets beginners who will learn basic and rigorous machine learning methods, including linear regression, logistic regression, decision trees, naïve Bayes, SVM, unsupervised learning, neural networks, graphical models, EM algorithm. The students will be able to enter more advanced machine learning courses after taking this course.
AIAA 5047
Responsible Artificial Intelligence
[3-0-0:3]
Background
Students are expected to have entry-level knowledge of AI, machine learning, or data mining.
Description
Artificial Intelligence technologies have been maturing and are deployed in real-world applications, such as healthcare, entertainment, business, scientific research, military, etc. In all these domains, the decisions made by AI algorithms can critically impact individuals, organizations and society. The designers, auditors, and users of AI technologies thus need to be equipped with the capabilities to understand, analyze, and eventually discipline these algorithms in the broader contexts. This course will introduce students to the latest research of responsible AI and explore these capabilities in both theoretical and practical ways. Topics include but are not limited to theories and algorithms of secure machine learning, fair machine learning, interpretable AI, and case studies involving natural language processing, computer vision, and reinforcement learning.
AIAA 5048
Multimodal Artificial Intelligence
[3-0-0:3]
Background
Basic programming skills.
Description
This course focuses on the Artificial Intelligence (AI) techniques and applications in multimodal tasks, which involve processing, fusing, and generating contents from multiple data modalities, such as images, videos, text etc. The course will cover the challenges, state-of-the-art methods, as well as hands-on experience in implementing and evaluating multi-modal deep learning models.
AIAA 5049
Applied Deep Learning: From Speech to Language and Multimodal Processing
[3-0-0:3]
Background
Familiar to use Python for the coding, and have fundamental knowledge of Multi-modal Learning.
Description
In the era of large-scale deep learning models, multimodal learning based on speech, text, and images is gaining increasing prominence. It holds the potential to facilitate cross-domain applications, improve human-computer interaction, and advance innovation in the field of AI. This course will provide an in-depth exploration of applied deep learning techniques, focusing on their applications in speech processing, natural language understanding, and multimodal data analysis. Students will gain practical experience in building deep learning models for various tasks, including speech recognition, language translation, image analysis, and more. The course covers fundamental concepts, algorithms, and tools in the field of deep learning and emphasizes hands-on projects and real-world applications.
AIAA 5050
Machine Consciousness
[3-0-0:3]
Background
Basic programming skills
Description
The study of consciousness is referred to as the "ultimate challenge of artificial intelligence." This course provides instruction and discussions in the field of machine consciousness. The main content includes an introduction to consciousness research, mainstream theories of consciousness, research on self-awareness, attention mechanisms, optimization of intelligent agent goals, subjectivity and affective computing, consciousness modeling and evaluation of artificial intelligence systems, and analysis and control of risks related to machine consciousness. Through this course, participants can gain a fairly comprehensive and in-depth understanding of the research history and current status of the field of machine consciousness, and engage in collaborative research on several specific issues.
AIAA 5072
Quantum Computing
[3-0-0:3]
Background
Familiar with Linear algebra and Probability Theory.
Description
This course provides a comprehensive introduction to the field of quantum computing. Students will explore fundamental concepts such as quantum bits, quantum circuits, and quantum algorithms. Advanced topics including quantum error correction, quantum information processing, and quantum machine learning will also be covered.
AIAA 5075
Information Theory for Machine Learning
[3-0-0:3]
Background
Familiarity with linear algebra and probability theory.
Description
In the era of big data and artificial intelligence, information theory has become an indispensable tool for machine learning practitioners. This course aims to bridge the gap between classical information theory and its cutting-edge applications in machine learning. Students will explore the foundations of information measures, data compression, hypothesis testing, channel coding, channel capacity, entropies, and divergences, as well as their statistical learning applications. Through guest lectures by leading experts, we will also delve into the frontiers of information theory in machine learning. By the end of this course, students will be equipped with the knowledge and skills necessary to apply information theory to develop more efficient and effective machine learning technologies.
AIAA 5088
Natural Language Processing and Its Applications
[3-0-0:3]
Description
This course offers an in-depth exploration of Natural Language Processing (NLP), emphasizing transformative neural network architectures like RNNs and transformers. Students will engage with core NLP tasks such as language modeling and machine translation, and examine the impacts of recent innovations like Large Language Models.
AIAA 6011
Topics in Artificial Intelligence
[1-4 credit(s)]
Description
Selected topics in Artificial Intelligence (AI) of current interest of current interest in emerging areas and not covered by existing courses. May be repeated for credit if different topics are covered. May be graded by letter or P/F for different offerings.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Recognize the current research trend in AI.
- 2.
  Explain the theories and applications in the chosen topics.
- 3.
  Apply the methodologies and techniques to real problems in the chosen topics.
AIAA 6021
Topics in Machine Learning
[3-0-0:3]
Description
Covers emerging topics of machine learning. Potential topics include machine learning and cognitive science, transfer learning, multi-task learning, active learning, lifelong learning, assemble learning, and advances in deep learning. Graded P or F.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Understand of recent developments in a specific area of machine learning.
AIAA 6090
Research Internship
[0 credit]
Description
The course will provide students with the opportunity to gain relevant knowledge, skills, and experience while establishing important connections in the field. Graded P or F.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Gain first-hand experience of AI application in the real-world.
AIAA 6091
Independent Study
[1-3 credit(s)]
Description
An independent research project carried out under the supervision of a faculty member. Graded P or F.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate understanding of recent developments in a specific area of AI.
AIAA 6101
Artificial Intelligence Seminar I
[0 credit]
Description
Series of seminars presenting research problems currently under investigation, presented by faculty, students, and visiting speakers. Students are expected to attend regularly. Graded P or F.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Understand current AI research trends and applications.
AIAA 6102
Artificial Intelligence Seminar II
[0-1-0:1]
Description
Series of seminars presenting research problems currently under investigation, presented by faculty, students, and visiting speakers. Students are expected to attend regularly. Continuation of AIAA 6101. Graded P or F.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Demonstrate an understanding of current AI research trends and applications.
AIAA 6990
MPhil Thesis Research
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.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Design, develop and conduct cross-disciplinary research in Artificial Intelligence.
- 2.
  Demonstrate practical skills in building AI systems.
- 3.
  Communicate research findings effectively in written and oral presentations.
AIAA 7990
Doctoral Thesis Research
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.
Intended Learning Outcomes
On successful completion of the course, students will be able to:
- 1.
  Design, develop and conduct cross-disciplinary research in Artificial Intelligence.
- 2.
  Critically apply theories, methodologies and knowledge to address fundamental questions in AI.
- 3.
  Demonstrate practical skills in building AI systems.
- 4.
  Communicate research findings effectively in written and oral presentations.

Back