For more details on the courses, please refer to the Course Catalog
| Code | Course Title | Credit | Learning Time | Division | Degree | Grade | Note | Language | Availability |
|---|---|---|---|---|---|---|---|---|---|
| AIM5055 | Bayesian learning | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | - | No | |
| In this course, students will learn Bayesian learning. Bayesian statistical methods help estimate probabilities and make decisions under uncertainty. And Bayesian Deep Learning, which combines the benefits of modern deep learning methods and modern Bayesian statistical methods, is emerging. Students will learn Bayesian learning at first and learn the Bayesian Deep Learning in more detail. | |||||||||
| AIM5056 | Machine learning with Graphs | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | English | Yes | |
| Machine learning with graphs is a quickly growing subfield of machine learning that seeks to apply machine learning methods to graph-structured data. Applications of machine learning on graphs include drug design, user profiling, and friendship recommendation in social networks. This course will provide an introduction to graph representation learning, including matrix factorization-based methods, random-walk based algorithms, and graph neural networks. During the course, we will study both the theoretical motivations and practical applications of these methods. | |||||||||
| AIM5058 | Variational Inference | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | Korean | Yes |
| The goal of inference problem is to find a structure hidden in the data. This can often be achieved by getting the posterior probability distribution which is intractable in many cases. Variational inference (VI) solve this by casting inference problem as an optimization. In this course, we explore VI and stochastic VI after learning basic probability theory and Monte-Carlo methods. The connection between VI and VAE is also provided. | |||||||||
| CHS5003 | Social Simulation based on Agent-based Modeling | 3 | 6 | Major | Master/Doctor | Challenge Semester | - | No | |
| The real world system consists of environment and various agents which are some kinds of objects. Each agent decides and acts according to its own decision process, and the system shows complex behaviors through interactions between the components (environment and agents). The social simulation using agent-based modeling is used to mimic the social phenomena (behaviors from interactions between agents), and used in various fields such as transportation, public health, and national defense industry. This course aims to learn the concepts and examples of social simulation using agent-based modeling. focusing on basic probability and statistics, population synthesis, agent-based modeling methodology, and the epidemic simulation. | |||||||||
| CHS7003 | Artificial Intelligence Application | 3 | 6 | Major | Bachelor/Master/Doctor | Challenge Semester | - | No | |
| Cs231n, an open course at Stanford University, is one of the most popular open courses on image recognition and deep learning. This class uses the MOOC content which is cs231n of Stanford University with a flipped class way. This class requires basic undergraduate knowledge of mathematics (linear algebra, calculus, probability/statistics) and basic Python-based coding skills. The specific progress and activities of the class are as follows. 1) Listening to On-line Lectures (led by learners) 2) On-line lecture (English) Organize individual notes about what you listen to 3) On-line lecture (English) QnA discussion about what was listened to (learned by the learner) 4) QnA-based Instructor-led Off-line Lecture (Korean) Lecturer 5) Team Supplementary Presentation (Learner-led) For each topic, learn using the above mentioned steps from 1) to 5). The grades are absolute based on each activity, assignment, midterm exam and final project. Class contents are as follows. - Introduction Image Classification Loss Function & Optimization (Assignment # 1) - Introduction to Neural Networks - Convolutional Neural Networks (Assignment # 2) - Training Neural Networks - Deep Learning Hardware and Software - CNN Architectures-Recurrent Neural Networks (Assignment # 3) - Detection and Segmentation - Generative Models - Visualizing and Understanding - Deep Reinforcement Learning - Final Project. This class will cover the deep learning method related to image recognitio | |||||||||
| CHS7004 | Thesis writing in humanities and social sciences using Python | 3 | 6 | Major | Bachelor/Master/Doctor | Challenge Semester | - | No | |
| This course is to write a thesis in humanities and social science field using Python. This course is for writing thesis using big data for research in the humanities and social sciences. Basically, students will learn how to write a thesis, and implement a program in Python as a research methodology for thesis. Students will learn how to write thesis using Python, which is the most suitable for processing humanities and social science related materials among programming languages and has excellent data visualization. Basic research methodology for thesis writing will be covered first as theoretical lectures. Methodology for selection of topics will be discussed also. Once a topic is selected, a lecture on how to organize related research will be conducted. In the next step, students learn how to write necessary content according to the research methodology. Then how to suggest further discussion along with how to organize bibliography to complete a theoretical approach. The basic Python grammar is covered for data analysis using Python, and the process for input data processing is conducted. After learning how to install and use the required Python package in each research field, the actual data processing will be practiced. To prepare for the joint research, learn how to use the jupyter notebook as the basic environment. Learn how to use matplolib for data visualization and how to use pandas for big data processing. | |||||||||
| COV7001 | Academic Writing and Research Ethics 1 | 1 | 2 | Major | Master/Doctor | SKKU Institute for Convergence | Korean | Yes | |
| 1) Learn the basic structure of academic paper writing, and obtain the ability to compose academic paper writing. 2) Learn the skills to express scientific data in English and to be able to sumit research paper in the international journals. 3) Learn research ethics in conducting science and writing academic papers. | |||||||||
| DAI4001 | Introduction to AI and Programming | 3 | 6 | Major | Bachelor/Master | Korean | Yes | ||
| For non-Communists who have no knowledge of programming, this course will understand the basic concepts of Python, a programming language for utilizing artificial intelligence, and foster the ability to carry out package and visualization for utilizing artificial intelligence and big data, as well as actual data analysis and applications. | |||||||||
| DAI5001 | Fundamentals of Artificial Intelligence | 3 | 6 | Major | Master/Doctor | 1-8 | - | No | |
| Artificial intelligence is a field of research into information processing models that can mimic human intelligence and cognitive functions. As a fundamental problem of artificial intelligence, it deals with theories and fundamental computational problems on the methods of empirical exploration, reasoning, learning and knowledge expression. It deals with logic-based proof of theorem, game theory, intelligent agent, etc., learns the basic principles of neural network, evolutionary computation, and beigean network, and examines areas such as expert system, computer vision, natural language processing, data mining, information search and bioinformatics as examples of its application. | |||||||||
| DAI5002 | Basic Programming for Artificial Intelligence | 3 | 6 | Major | Master/Doctor | 1-8 | Korean | Yes | |
| For non-Communists who have no knowledge of programming, this course will understand the basic concepts of Python, a programming language for utilizing artificial intelligence, and foster the ability to carry out package and visualization for utilizing artificial intelligence and big data, as well as actual data analysis and applications. | |||||||||
| DAI5003 | Mathematics for Artificial Intelligence | 3 | 6 | Major | Master/Doctor | 1-8 | Korean | Yes | |
| This subject is a subject that acquires basic mathematics/statistics needed to understand and utilize artificial intelligence for new students entering the artificial intelligence convergence department, and is a statistical foundation for the free use of artificial intelligence in the future. In other words, through this course, students learn the mathematics required to understand machine learning in conjunction with programming. For this purpose, this class will cover essential requirements for machine learning and courses, such as algebra, calculus, linear algebra, and geometry. | |||||||||
| DAI5004 | Advanced Machine Learning and Deep Learning | 3 | 6 | Major | Master/Doctor | 1-8 | Korean | Yes | |
| In this course, you will learn about machine learning, deep learning, and associated optimization techniques, as well as basic neural networks. And the core models of video processing and natural language processing learn about the theory, application and practice of CNN and RNN. | |||||||||
| DAI5005 | Advanced Data Mining | 3 | 6 | Major | Master/Doctor | 1-8 | - | No | |
| Data mining has recently received much attention as a necessary tool for big data analysis. Learning the technology to design and implement advanced data mining algorithms and analytical platforms, especially in artificial intelligence and computer engineering, plays a key role in deriving valuable knowledge in big data and data science. This subject deals with computer science, data science-based advanced technology, algorithms and key platforms for this. It also learns techniques that effectively analyze super-capacity data, super-fast data, etc. | |||||||||
| DAI5006 | Advanced Natural Language Processing | 3 | 6 | Major | Master/Doctor | 1-8 | - | No | |
| In this course, students are required to Implement programs that can manipulate, analyze, and process language data using Python and machine learning & deep learning models. After taking the course, student can - Explain key concepts from NLP and linguistics - Design data structures appropriate for storing natural language data - Understand how deep learning and machine learning algorithms are used for solving NLP problems - Build program for text classification, clustering, and generation using machine learning and deep learning algorithms - Evaluate the performance of NLP techniques | |||||||||
| DAI5007 | Interdisciplinary Service Design Process | 3 | 6 | Major | Master/Doctor | 1-8 | - | No | |
| This class aims to investigate how to build service design procedures with economic/environmental/experimental perspectives toward customer services. Moreover, a set of interactions and stakeholders’ touchpoints are examined. Moreover, team-based projects, which focus on service design procedures, are conducted for presenting customer data analytics, and examining customer experience in the services, based on the understanding on artificial intelligence and data mining (Pre-required class: Introduction to Artificial Intelligence, Advanced Data Mining, Advanced Machine Learning and Deep Learning). | |||||||||