For more details on the courses, please refer to the Course Catalog
| Code | Course Title | Credit | Learning Time | Division | Degree | Grade | Note | Language | Availability |
|---|---|---|---|---|---|---|---|---|---|
| AIM5026 | Introduction to Robotic Intelligence | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | - | No | |
| Robot is defined as an intelligent system connecting sensors and actuators. As an intelligent system, robot is to play a key role for providing necessary services to human by automatically carrying out tasks requiring navigation and manipulation. To this end, robot needs to recognize objects and understand surroundings while reasoning and planning the behaviors necessary for carrying out tasks. Especially, it is essential for robot to be able to obtain its capabilities of recognition and understanding of environments as well as of reasoning and planning of behaviors by learning. This course deals with the fundamentals of robot intelligence on how robot learns for the recognition and understanding of environments as well as for the reasoning and planning of behaviors associated with manipulation and navigation. | |||||||||
| AIM5036 | Deep Generative Model | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | Korean | Yes | |
| We cover the topics on deep generative models, which are attracting lots of attention. First part include autoregressive models, variational autoencoder (VAE), normalized flow, and the second half will be dedicated to generative adversarial networks (GAN) and its variations such as Wasserstein GAN, conditional GAN, and Cycle GAN, et. We will also cover various application areas that utilize generative models. | |||||||||
| AIM5039 | Intelligent Storytelling | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | - | No | |
| In this course students will learn theories on interactive storytelling, computational models of interactive narrative based on AI technology, and practice/demonstration/exercise on interactive storytelling systems and authoring tools. After taking the class, students should be able to apply theoretical narrative models, AI techniques, and authoring tools for building interactive narrative systems. In addition, they are expected to propose and evaluate research ideas in interactive storytelling systems | |||||||||
| AIM5042 | Game AI | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | - | No | |
| Artificial intelligence is one of the essential components of a computer game, and computer games can be referred as testbeds for human-level intelligence of computers. This lecture introduces various game AI techniques including state machines, decision making algorithms for both realism and entertaining experiences, path finding, and strategy making. | |||||||||
| AIM5044 | Neuromorphic Processor | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | - | No | |
| The purpose of the Neuromorphic Processor is to learn a variety of techniques for designing neuromorphic systems mimicking the structure and behavior of a biological brain. After understanding the structure and behavior of a biological brain, the students will learn about the basic properties of memristive devices and CMOS circuits as important tools to implement neuromorphic systems. The lecture also deals with the architectures and operation principles of current neuromorphic processors, and learns how to design low-power high-performance neuromorphic processors. | |||||||||
| AIM5053 | AI and Ethics | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | - | No | |
| In this course, students will analyze AI models' limitations in terms of ethics and learn how to overcome the limitations. Every technology has an intended use and unintended consequences. For example, nuclear power makes power plants and atomic bombs. AI also has this dual-use. Students will learn the problem of dual-use in AI and understand and suggest solutions. | |||||||||
| AIM5054 | Computational Social Science | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | - | No | |
| In this course, students will learn computational social science (CSS). CSS is the intersection of computer science, statistics, and social science. It solves the research problem in social science by computational methods, especially AI. Students will learn the research problems and AI models in CSS. | |||||||||
| 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. | |||||||||
| AIM5057 | Knowledge Graph-based Methods | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | - | No | |
| This course is to learn foundations, techniques, and algorithms for building and leveraging knowledge graphs. Students will study the theory and applications of the techniques needed to build and query massive knowledge graphs. Topics include crawling web sites, wrapper learning, information extraction, source alignment, string matching, entity linking, graph databases, querying knowledge graphs, data cleaning, Semantic Web, linked data, graph analytics, and intellectual property. | |||||||||
| 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. | |||||||||
| AIM5065 | OPEN AI NETWORKING | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | English | Yes |
| Mobile/wireless networks are going through a new AI revolution triggered by the challenges of hyper-connectivity, hyper-low latency communication, and massive data orchestration for enormous connected objects. As such, they are one of the most active research areas in Beyond 5G and 6G in terms of growth and innovation. The “AI and 5G/6G” course covers basic knowledge of 5G/6G mobile networks and available AI technologies for improved network performance and efficient management of resources. In particular, the course is split in three parts, where the first part discusses basic 5G architecture and new technologies that are shaping 6G architecture, such as cloud-native computing, AI-native communication, and deterministic networking. Second part covers the state-of-the-art Deep Learning (DL) approaches that are relevant for 5G/6G mobile networks, like recurrent models, generative adversarial networks, transformer networks, and deep reinforcement learning. Third part presents the latest case studies of AI based dynamic orchestration of network behavior by using parameters like traffic variation, localization, mobility, and user context. At the end of the course, the student will have a comprehensive vision of 5G/6G mobile networks and relevant state-of-the-art AI technologies that open up numerous industrial, management, and research opportunities. | |||||||||
| AIM5066 | Large Language Models | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | Korean | Yes |
| Large language models (LLMs) have actively undergone a revolutionary transformation in the field of natural language processing (NLP). Serving as the cornerstone for cutting-edge systems, these models have become pervasive in addressing a diverse array of tasks related to natural language understanding and generation. While LLMs exhibit unprecedented potential and capabilities, they also give rise to new challenges, particularly in the realms of ethics and scalability. This course is designed to delve into the forefront of research, focusing on pre-trained language models. We will explore their technical underpinnings, including models such as BERT, GPT, T5, mixture-of-expert models, and retrieval-based models. Additionally, we will investigate emerging capabilities like knowledge integration, reasoning abilities, few-shot learning, and in-context learning. The curriculum will extend to cover aspects such as fine-tuning and adaptation, and the crucial dimensions of security and ethics. We will thoroughly examine each topic and engage in in-depth discussions of influential papers. Students will actively participate by routinely reading and presenting research papers. | |||||||||
| 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. | |||||||||
| DMC5007 | On-device Deep Learning | 3 | 6 | Major | Master/Doctor | 1-4 | Digital Media Communication | - | No |
| This course pursues in-depth study on deep neural network (DNN) compression techniques for on-device deep learning, which allows smartpones and IoT devices to execute DNN applications. The detailed topics include DNN pruning, low-precision bit quantization, and neural network architecture search (NAS). | |||||||||