At least 33 credits in total
Mandatory General Course 3 credits and 1AU |
|
---|---|
Elective Course at least 21 credits |
|
Research Credits at least 9 credits |
|
At least 63 credits in total
Mandatory General Course 3 credits and 1AU |
|
---|---|
Elective Course at least 30 credits |
|
Research Credits at least 30 credits |
|
This course lays statistical foundation for data scientists. Probability model, random variables and their probability distribution, joint distribution, and conditional distribution are introduced along with data generation from a given distribution via computer exercise. Statistical inference with likelihood principle and Bayesian approach will be covered.
This is an introductory course on machine learning, which belongs to a broader family of machine learning methods concerned with the development and application of modern neural networks. We will cover a range of topics from basic neural networks, convolutional and recurrent network structures, deep unsupervised learning, attention-based models, and applications to computer vision, language understanding, and other areas. The course will be focused on understanding deep learning methodology, rather than implementing them using modern libraries.
This course introduces the technologies and programming techniques for data science. This course covers from the programming language basics, which is effective in data science, common libraries for analytics, and utility tools and techniques on software for data science.
There has been an increasing trend towards integrating sensing, storing, and computing in the real world. This course takes an interdisciplinary look at this pervasive computing from the data science perspective. A huge set of data is being collected, stored, and analyzed via sensors, SNSs, metaverse, etc. Students are expected to understand how to integrate the data science into the sensing, collecting, and analyzing such data in an impactful way.
This course is a project-based course focused on recommender systems and machine learning on graphs. The first half of the course covers fundamental techniques in recommender systems ranging from content-based approaches, and traditional collaborative filtering, to recent advanced techniques including matrix factorization and deep learning-based collaborative filtering methods. In the second half of the course, we discuss major topics in machine learning on graphs including random walk-based methods