Academics

Academics
Academics

Descriptions of Courses


AI501 Machine Learning for AI
In this course, we will learn about introductory materials for machine learning, which is the fundamental and core technology for current generation of artificial intelligence. We will cover the most fundamental ideas and theories of machine learning, and introduce some of the important topics that will be covered in more advanced courses. Specifically, we will cover mathematical backgrounds for machine learning, fundamental concept of machine learning, supervised learning methods (regression & classification), unsupervised learning methods (clustering & dimensionality reduction), ensemble models, Bayesian approaches and models, neural networks, and reinforcement learning.

AI502 Deep Learning
In this course, we will learn about introductory materials for deep learning, which is a machine learning methodology that learns multiple layers of non-linear representations for given prediction tasks, while reviewing some of its applications to computer vision and natural language processing. The course will be mostly focused on understanding deep learning methodology, rather than implementing and using existing deep learning frameworks. We will have three to four lab courses on Tensorflow basics.

AI503 Mathematics for AI
In this lecture, I plan to introduce elementary mathematical concepts frequently used for the area of artificial intelligence. In particular, I will explain some introductory parts of linear algebra, multi-variate calculus, probability(or statistics), algorithms, complexity theory and information theory which are useful to building machine/deep learning models with corresponding applications.

AI504 Programming for AI
Programming for AI aims to introduce several programming languages for deep neural networks and deep probabilistic models. Topic covered includes various deep learning models and probabilistic inference on the programming platform.

AI505 Optimization for AI
Machine learning algorithms in general train their parameters from training data by optimizing their objective functions. This course covers optimization methods with examples of machine learning algorithms.

AI506 Data Mining and Search
Huge amounts of data are being generated everyday, and data-driven decision-making becomes increasingly important. The course covers a variety of topics in data mining, search, exploration, and preprocessing, with a focus on efficient algorithms and tools.

AI601 Advanced Machine Learning for AI
Machine learning, a sub-field of computer science, has been popular with the era of intelligent softwares and attracted huge attentions from computer vision, natural language processing, healthcare and finance communities to name a few. This course will consider the art of designing good learning algorithms, as well as analyzing an algorithm’s computational and statistical properties / performance guarantees. We will also discuss topics such as nonparametric density estimation, nonparametric regression, and Bayesian estimation, and derive the framework for target applications such as privacy, causality, and stochastic learning algorithms.

AI602 Advanced Deep Learning
In this lecture, I plan to cover recent advances in the field of deep learning. Neural networks have been used for many applications in artificial intelligence for more than 30 years. However, due to powerful computing powers and large-scale datasets available nowadays, the field currently made breakthroughs via new techniques, in particular, for last 5 years. I will introduce them as well as their applications.

AI603 Machine Learning Theory
This course covers both classical and recent machine learning theory. In this course we provide fundamental ideas and theoretical frameworks so that students can understand and analyze complexity of algorithms and performance bounds for machine learning algorithms.

AI604 Deep Learning for Computer Vision
This is an introductory course on deep learning for computer vision with emphasis on understanding of convolutional neural networks and their applications to visual recognition tasks such as image classification, localization, and detection. The students will perform term projects, where they implement their own networks using deep learning libraries for their choices of computer vision problems.

AI605 Deep Learning for Natural Language Processing
Natural language processing (NLP), which aims at properly understanding and generating human languages, emerges as a crucial application of artificial intelligence, with the advancements of deep neural networks. This course will cover various deep learning approaches as well as their applications such as document classification, machine translation, question answering, and dialog systems.

AI606 Recommender Systems
As people are confronted with unprecedented amounts of information, recommender systems, which provide people with relevant information, become indispensable to support their decision-making process. The course covers a variety of topics in recommender systems, including collaborative filtering, content-based filtering, and scalability issues.

AI607 Graph Mining and Social Network Analysis
Graphs are ubiquitous, representing a variety of information: online social networks, e-commerce purchase history, the World Wide Web, to name a few. This course covers a variety topics related to understanding, analyzing and utilizing graph data, with a focus on efficient algorithms and AI problems on graphs. The course also introduces related studies in Physics and Social Science.

AI608 AI-based Time Series Analysis
This course provides a survey of the theory and application of time series methods. Topics covered include stationary and non-stationary models, auto regressions, multivariate time series, deep neural models for time series, inference in persistent time series and structural break. Real-world data in finance, manufacturing and healthcare will be provided for practice.

AI609 Parallel and Distributed Computation for AI
In this course, students will learn mathematical theories associated with parallel and distributed computation often arising in modern artificial intelligence. In particular, iterative algorithms and their distributed implementation, convergence, and communication and synchronization among processing nodes, focusing on asynchronous parallel and distributed algorithms. System of equations, nonlinear optimization, variational inequality problem, shortest path problem, dynamic programming, and network flow problem will be addressed as applications.

AI610 Sequential Decision Making under Uncertainty
The subject of this course is sequential decision making under uncertainty in a system whose evolution is influenced by decisions. The decision made at any given time depends on the state of the system and the objective is to select a decision making rule that optimizes a certain performance criterion. Such problems can be solved, in principle, using the classical methods of dynamic programming. In practice, however, the applicability of dynamic programming to many important problems is limited by the enormous size of the underlying state/action spaces as well as uncertainties in the system. “Neuro-dynamic programming” or “Reinforcement Learning” which is the term used in the Artificial Intelligence literature, uses neural networks and other approximation architectures to overcome such bottlenecks to the applicability of dynamic programming, while using Mote Carlo estimation and/or stochastic approximation to learn models or value functions of the system. The methodology allows systems to learn about their behavior through simulation, and to improve their performance through iterative reinforcement. The focus of this course is to understand the mathematical foundations of this methodology in light of the convergence, degree of suboptimality, computational complexity and sample efficiency of different algorithms.

AI701 Bayesian Machine Learning
Bayesian Learning conducts model reserach and predictive inference based on Bayesian principles. Topics covered include variational Bayesian inference, Bayesian hierarchical models, Bayesian optimization and Bayesian deep learning.

AI702 Interpretability and Interactivity in AI
Interpretability and interactivity of artificial intelligence techniques emerge as important issues. This course will cover various model interpretation approaches and interactive user interfaces applicable to deep neural networks, the core techniques in artificial intelligence.

AI960 M.S. Thesis Research
Discussions with academic advisor, checking of research progress, and presentation of the current status of thesis progress are made for improved research content of the dissertation.

AI966 M.S. Seminar
This course will provide an exclusive opportunity to meet with professionals who are working in forefront of various fields. With this course, the students will keep up with the latest developments and trends in the fields of AI and others.

AI980 Ph.D. Thesis Research
Discussions with academic advisor, checking of research progress, and presentation of the current status of thesis progress are made for improved research content of the dissertation.

AI986 Ph.D. Seminar
This course will provide an exclusive opportunity to meet with professionals who are working in forefront of various fields. With this course, the students will keep up with the latest developments and trends in the fields of AI and others.

Table of Curriculum


Classification Course No. Code Course Name Credit(s)
(Homework)
Semester Remark
Mandatory
Major Courses
AI501 F2.501 Machine Learning for AI 3:0:3 Spring and Fall
AI502 F2.502 Deep Learning 3:0:3 Spring and Fall
Elective
Major Courses
AI503 F2.503 Mathematics for AI 3:0:3 Spring or Fall
AI504 F2.504 Programming for AI 3:0:3 Spring or Fall
AI505 F2.505 Optimization for AI 3:0:3 Spring or Fall
AI506 F2.506 Data Mining and Search 3:0:3 Spring or Fall
AI601 F2.601 Advanced Machine Learning for AI 3:0:3 Spring or Fall
AI602 F2.602 Advanced Deep Learning 3:0:3 Spring or Fall
AI603 F2.603 Machine Learning Theory 3:0:3 Spring or Fall
AI604 F2.604 Deep Learning for Computer Vision 3:0:3 Spring or Fall
AI605 F2.605 Deep Learning for Natural Language Processing 3:0:3 Spring or Fall
AI606 F2.606 Recommender Systems 3:0:3 Spring or Fall
AI607 F2.607 Graph Mining and Social Network Analysis 3:0:3 Spring or Fall
AI608 F2.608 AI-based Time Series Analysis 3:0:3 Spring or Fall
AI609 F2.609 Parallel and Distributed Computation for AI 3:0:3 Spring or Fall
AI610 F2.610 Sequential Decision Making under Uncertainty 3:0:3 Spring or Fall
AI701 F2.701 Bayesian Machine Learning 3:0:3 Spring or Fall
AI702 F2.702 Interpretability and Interactivity in AI 3:0:3 Spring or Fall
Research AI960 F2.960 M.S. Thesis Research - Spring or Fall
AI966 F2.966 M.S. Seminar 1:0:1 Spring or Fall
AI980 F2.980 Ph.D. Thesis Research - Spring or Fall
AI986 F2.986 Ph.D. Seminar 1:0:1 Spring or Fall

◎: A Course mutually recognized by undergraduate and graduate programs.

For Master’s Program

Major Course Requirements for Graduate School of Artificial Intelligence (For Master’s Program)

Thesis Master’s Degree Program
*Please check the common graduate course requirements
  • Credit Requirement for Graduation:
    – Required to complete a total of more than 33 credits
  • Mandatory General Courses: At least 3 credits and 1AU
    – No designated course by the department, mandatory to take 1 course among ‘Mandatory general course’,
    – ‘CC010 Special Lecture on Leadership’ (non-credit course, general scholarship students and foreign students are excluded)
    – ‘CC020 Ethics and Safety I’(1AU): Mandatory for graduation
    ※ Not required for Doctoral course students if taken during the Master’s degree program
  • Mandatory Major Courses: 6 credits
    – AI501 Machine Learning for AI, AI502 Deep Learning
  • Elective Courses: At least 15 credits
  • Research Courses: At least 9 credits
    – AI966 M.S. Seminar(at least 2 credits)
    – only courses with the subtitle are accepted
    ※ Foreign students and general scholarship students are exempt from seminar credits

For Doctoral Program

Major Course Requirements for Graduate School of Artificial Intelligence (For Doctoral Program)

*Please check the common graduate course requirements
  • Credit Requirement for Graduation:
    – Required to complete a total of more than 60 credits
  • Mandatory General Courses: At least 3 credits and 1AU
    – (Same as Master’s Program requirements)
  • Mandatory Major Courses: 6 credits
    – AI501 Machine Learning for AI, AI502 Deep Learning
    ※ Not required for Doctoral course students if taken during the Master’s degree program
  • Elective Courses: At least 21 credits
    – Credits taken in the master’s program can be accumulatively counted
  • Research Courses: At least 30 credits
    – AI986 Ph.D. Seminar(at least 4 credits)
    – only courses with the subtitle are accepted
    ※ Foreign students and general scholarship students are exempt from seminar credits

For MS-Ph.D Integrated Program

Major Course Requirements for Graduate School of Artificial Intelligence (For MS-Ph.D Integrated Program)

*Please check the common graduate course requirements
  • For MS-Ph.D Integrated Program:
    – Required to complete a total of more than 60 credits
  • Mandatory General Courses: At least 3 credits and 1AU
    – (Same as Master’s Program requirements)
  • Mandatory Major Courses: 6 credits
    – AI501 Machine Learning for AI, AI502 Deep Learning
    ※ Not required for Doctoral course students if taken during the Master’s degree program
  • Elective Courses: At least 21 credits
    – Credits taken in the master’s program can be accumulatively counted
  • Research Courses: At least 30 credits
    – AI966 M.S. Seminar or AI986 Ph.D. Seminar(at least 5 credits)
    – only courses with the subtitle are accepted
    ※ Foreign students and general scholarship students are exempt from seminar credits