Instructor: Yihan Gao

This course offers a broad coverage of topics in the field of data mining. The first half of the course cover basic data mining concepts including: data preparation, knowledge presentation, classification, clustering, generalization of algorithms, evaluation of credibility, and association analysis. The second half of the course covers some of the more advanced research topics in the field of data mining. This course intends to be a first course on data mining that prepares students for further study, which introduces students to many different topics so that they can pursue their favorite ones on their own after the course.

Instructor: Kaisheng Ma

This is a course focusing both on theoretical and experimental hardware fundamentals. The target is to implement small scale convolution operation in CNN on FPGA. After the course, students should be able to handle: How to divide control logics and computing logics. How to implement logics, timing, state-machine etc. Able to make testbenches. Able to map to FPGA, and debug on it. Know basics about back-end about ASIC chip design, like verification, layout etc. Able to implement a 3*3 convolution layer, and finish the local memory, global memory. 

Instructor: Yi Wu, Yang Gao

This course aims at providing freshmen students with a broad overview of the Artificial Intelligence field, including computer vision, robotics, reinforcement learning, AI systems, and AI algorithms, motivating them to study the field, and encouraging them to conduct indepth investigation on different areas of the field. It is a required course for freshmen students in the Special Artificial Intelligence Polit Class. Lectures will be given by leading experts in AI areas from both academia and industry.

Instructor: Yuhao Wang

Statistical methodsoffer a powerful toolkit to extract useful information from massive and noisy observational data. This course introduces studentstomodern statistical methods and their theoretical foundations in high-dimensional and nonparametric models. In this course, we will covermodern statistical methods developed over the past 20 years, analyzetheir asymptotic properties and probabilistic foundations, and show how these methods can be applied into real data applications. Selected topicsinclude:high-dimensional and nonparametric estimation, minimax lower bound, multiple hypothesis testing, semiparametric models.

Instructor: Huanchen Zhang

This course is designed to introduce the fundamental concepts and implementations of modern database management systems. This is not a course that teaches you how to build database applications (e.g., schema design, SQL programming). It is designed as a systems course, with an emphasis on database internals. Topics include relational model and SQL, storage and indexing, query processing and optimization, transactions and concurrency control, distributed and cloud databases, as well as advanced research topics in the field. Students taking this course should have basic knowledge on computer systems. No prior database experience is assumed. The course consists of lectures, written assignments, and projects. Assignments and projects are designed to reinforce what the student learned in lectures and to provide hands- on experience in building a database system. Upon successful completion of this course, the student should feel confident taking a job as a database developer or conducting database-related research in graduate school.

Instructor: Zhilin Yang

This course will introduce important problems in the field of natural language processing such as language modeling, machine translation, and question answering, as well as core technologies to solve these problems including attention-based neural networks and language model pretraining. The course will cover basic algorithms, real-world applications, as well as open problems in academic research.