Computer Science

This course is an introduction for undergraduate students who are interested in empirical methods applied to natural language processing. We will emphasize on empirical methods, which mainly refers to data-driven models with ingredient from pattern recognition and machine learning. We will also survey interesting NLP applications, e.g., word segmentation, tagging, parsing, etc., and introduce recent advances in statistical machine translation and information extraction. In this course, students will learn what data-driven methods are, how to utilize those models to build their own systems to analyze massive text data and actually solve a real NLP problem in practice. T

This course provides a comprehensive perspective on large language models. Specifically, in the first half, it covers the fundamentals of language models, including network structures, training, inference, and evaluation. In the second half, the course focuses on the interpretation of large language models, alignment, and their applications beyond simple text generation. Through this approach, the course equips students with foundational knowledge of the technologies behind large language models, helping them smoothly engage in research or practical applications in this field. Topics include Introduction and basics of large language models, Preprocessing: tokenization and data curation, Pre-training of large language models, Scaling laws and emergent behavior, Alignment: instruction tuning and preference learning, Learning from AI feedback, Decoding algorithms, Reasoning with test-time inference methods, Retrieval-augmented generation, AI agents, and Extension to multi-modality. 

Prerequisites: Machine learning, Deep learning

This is a project-oriented class covering trending and novel Human-Computer Interaction (HCI) research topics. This course focuses on Human-centered AI. 

The course surveys recent award-winning HCI papers for insight, with students undergoing through a complete HCI research cycle: Identifying a research question and reviewing related work to exploring solution design spaces; prototyping; conducting user studies, and writing a short paper. 

Previous class projects have been published in top HCI conferences (e.g., ACM CHI, UIST, SIGGRAPH, and MobileHCI) and have received multiple Best Paper/Honorable Mention awards. 
 

After taking the course, students would be able to master basic knowledge and skills about deep learning, construct basic DL models for solving various science and engineering problems, and understand the cutting edge research papers.

This course examines the general features of the A.I. problem solving process, and in particular the various forms of heuristic, together with their implementation and case studies of real systems.

This course offers an introduction to software engineering including software modeling languages, the software development process--workflow modeling, project planning and management, and requirements analysis and specification--software requirements modeling.

This is a research-oriented course for cybersecurity, a broad, fast, evolving discipline. The course covers important concepts but it not meant to be comprehensive. The following topics will be covered:

• The applied aspects of cryptographic primitives (randomness, hash, MAC, encryption, digital signatures)
• Cryptographic protocols (key exchange, authentication, anonymous communication, privacy-enhancing technologies)
• Network security (TCP/IP, DNS, BGP, TLS, DDoS, wireless, email, MLS)
• Advanced topics: _ security (IoT, SDN, blockchain, web, software, systems,...)

Course prerequisites: Basic knowledge in discrete mathematics, programming, and networking is strongly recommended. Class participants are also expected to comprehend research papers and conduct a research project. 

This course serves as an introductory course to high-level language programming, specifically designed for students with no prior experience. It can also act as a foundational course for other information-related subjects. The goal is for students to grasp the fundamental concepts and methods of object-oriented programming, understand the basic syntax and programming techniques of C++, learn to use integrated development environments, master program debugging methods, gain a preliminary understanding of common data structures and non-numerical algorithms, and get an initial introduction to the usage of the C++ Standard Template Library (STL).

This course examines AI concepts, including how to interact with AI systems, and critically evaluate their impact. It covers the ethical, social, and technological dimensions of AI. 

This course will focus on the advanced technologies in 3D visual computing in the era of big data. The course will cover a brief introduction to the basic concepts in the geometric analysis including curve, surface, 3D representations, 3D transformations, etc., with the goal of fostering students’ geometric understanding of 3D data. …