Master of Science in Artificial Intelligence

Course Description

Foundations of Machine Learning (3 Credits)

This course aims to provide students with a solid theoretical foundation and core skills in machine learning. The curriculum will systematically introduce the fundamental concepts and major paradigms of machine learning, including supervised learning (e.g., regression, classification), unsupervised learning (e.g., clustering, dimensionality reduction), as well as model evaluation methods, an introduction to learning theory, and the basic workflow for implementing machine learning projects. Students will learn how to select appropriate models to solve real-world problems and understand the principles, advantages, and limitations of different algorithms. Through a combination of theoretical lectures, case studies, and programming practice, this course will lay a crucial foundation for students' subsequent study of more advanced machine learning topics (such as deep learning, reinforcement learning, etc.).

AI Technology and Applications (3 Credits)

This course provides a comprehensive introduction to the fundamental theories, core technologies, and diverse applications of artificial intelligence. Starting with the history and philosophical considerations of AI, the content covers key models including search algorithms, knowledge representation and reasoning, machine learning (supervised, unsupervised, and reinforcement learning), and deep learning. Through a variety of case studies, the course will demonstrate the potential of AI in fields such as expert systems, natural language processing, computer vision, and autonomous systems, aiming to cultivate students' comprehensive ability to analyze problems, select appropriate AI technologies, and build solutions.

Mathematics for AI (3 Credits)

This course aims to provide students with the key mathematical tools and theoretical foundations required for the study of artificial intelligence. The content primarily covers the parts of linear algebra, multivariable calculus, probability theory, statistical inference, and optimization theory that are closely related to machine learning. The course emphasizes the practical application of mathematical concepts in artificial intelligence algorithms, helping students understand the mathematical principles behind the algorithms and laying a solid mathematical cornerstone for subsequent advanced courses.

Deep Learning (3 Credits)

This course provides an in-depth exploration of the theory, models, and applications of deep learning. The content covers core architectures such as Multilayer Perceptrons (MLPs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Transformer models, and Generative Adversarial Networks (GANs). Combined with practical case studies, the course will guide students to understand the powerful capabilities of deep learning in fields like computer vision and natural language processing, and to master the skills of designing, training, and tuning models using mainstream deep learning frameworks.

Programming and Tools for Machine Learning (3 Credits)

This course focuses on developing students' practical programming abilities and tool-handling skills in the field of machine learning. Centered around the Python language, the course will systematically introduce the use of common data science and machine learning libraries such as NumPy, Pandas, Matplotlib, and Scikit-learn. Students will learn the entire workflow of data acquisition, cleaning, processing, visualization, as well as machine learning model implementation, evaluation, and deployment, thereby building a solid engineering foundation for developing real-world machine learning projects.

Optimization for Machine Learning (3 Credits)

This course delves into the optimization theories and algorithms commonly used in machine learning. The content includes convex optimization fundamentals, gradient descent and its variants (such as stochastic gradient descent, Adam), Newton's method, and constrained optimization methods. The course will focus on the application, convergence analysis, and practical challenges of these optimization algorithms in training various machine learning models (such as linear models, support vector machines, and neural networks).

Natural Language Processing (3 Credits)

This course introduces the fundamental concepts, core technologies, and cutting-edge applications of Natural Language Processing (NLP). The content covers text preprocessing, word representations (e.g., Word2Vec, GloVe), language models, text classification, sentiment analysis, machine translation, question answering systems, and deep learning-based NLP models (e.g., RNNs, LSTMs, Transformers). Students will learn how computers can be used to process, understand, and generate human language.

Computer Vision (3 Credits)

This course aims to introduce the fundamental principles, key technologies, and typical applications in the field of computer vision. The content includes image processing fundamentals, feature extraction and description, image classification, object detection, image segmentation, face recognition, and 3D vision. The course will emphasize the application of deep learning methods (especially Convolutional Neural Networks) in solving computer vision problems and will guide students through related practical exercises.

Reinforcement Learning (3 Credits)

This course systematically introduces the theoretical framework and core algorithms of reinforcement learning. The content covers Markov Decision Processes (MDPs), dynamic programming, Monte Carlo methods, temporal-difference learning (e.g., Q-learning, SARSA), policy gradient methods, and deep reinforcement learning (e.g., DQN, A3C). Through practical examples, the course will explain the application of reinforcement learning in domains such as gaming, robotics control, and recommendation systems.

Time Series Analysis (3 Credits)

This course focuses on methods for analyzing and modeling time series data. The content includes the characteristics of time series (e.g., stationarity, autocorrelation), classical statistical models (e.g., ARIMA, exponential smoothing), spectral analysis, and methods for time series forecasting and anomaly detection based on machine learning and deep learning. The course emphasizes the integration of theory and practice, enabling students to handle time series data from fields such as finance, meteorology, and the Internet of Things (IoT).

Data Mining (3 Credits)

This course introduces the principles and techniques for discovering useful knowledge and patterns from large-scale data. The content covers core data mining tasks such as data preprocessing, association rule mining, classification, clustering, and anomaly detection. The course will discuss the applicable scenarios, advantages, and disadvantages of various data mining algorithms and, through case studies, cultivate students' ability to use data mining techniques to solve practical business and research problems.

Stochastic Processes (3 Credits)

This course provides the mathematical foundation for understanding and analyzing random phenomena that evolve over time. Key topics include a review of probability theory, Markov chains (both discrete and continuous-time), Poisson processes, renewal theory, an introduction to queueing theory, and Brownian motion. The course emphasizes the modeling and application of stochastic processes in fields such as machine learning, operations research, and financial engineering.

Special topics in Cutting-Edge AI (3 Credits)

This course aims to introduce the most recent and influential research directions and technological advancements in the field of artificial intelligence. The special topics may be dynamically adjusted each year, covering areas such as Trustworthy AI (fairness, interpretability, robustness), Automated Machine Learning (AutoML), Meta-Learning, Graph Neural Networks, Quantum Machine Learning, and Large Language Models. The course will be primarily based on seminars and reading of cutting-edge papers to stimulate students' research interests.

Special topics in AI Applications (3 Credits)

This course focuses on the in-depth application and practice of artificial intelligence in specific industries or interdisciplinary fields. The special topics may include smart healthcare, financial technology (FinTech), intelligent manufacturing, recommendation systems, autonomous driving, and smart cities. Through case analysis and project-based practice, the course will explore the selection of AI technologies, deployment challenges, and value creation in specific application scenarios.

Special topics in AI Systems (3 Credits)

This course focuses on the engineering challenges and solutions for building, deploying, and maintaining large-scale, high-performance AI systems. Special topics may include AIOps (AI for IT Operations), data engineering, model compression, distributed training and serving, and robotic systems, exploring the integration of Robot Operating System (ROS), sensor fusion, Simultaneous Localization and Mapping (SLAM), and Sim-to-Real (training in simulation and deploying in the real world). The course emphasizes systems design thinking and the practical engineering ability to solve complex problems.

Literature Review and Thesis Proposal (2 Credits)

This foundational component prepares students for their Master's Thesis. It is a structured process designed to guide students in identifying a viable research topic within the field of AI. Students will conduct a comprehensive and critical survey of existing scholarly work to understand the current state of research, identify a significant gap in knowledge, and formulate a precise research question. The process culminates in the development of a formal thesis proposal, which will serve as the blueprint for the subsequent thesis research. This proposal will detail the research objectives, methodology, and a projected timeline.

Social Ethics and Academic Special Project (1 Credit)

This multifaceted course explores the critical intersection of AI with society, law, and ethics. It aims to raise awareness and foster critical reflection on the societal impacts of AI technologies. Topics include fairness, accountability, transparency, algorithmic bias, data privacy, and the influence of AI on public policy and human rights. The course may combine theoretical learning with a practical "Special Project," an opportunity for students to conduct an in-depth investigation into a specific topic of interest. This project allows students to apply their analytical skills to a real-world case study, policy analysis, or the development of a novel application with ethical considerations at its core.