Curriculum
| Course Number | Summary | English |
|---|---|---|
| AI7001 | AI and Ethics | |
| This course provides the ethical responsibility in the use of artificial intelligence technology and research. | ||
| AI7002 | Advanced Probability and Random Variables | |
| This course provides various distributions including Gaussian and Poisson, conditional probability, Bayesian theory, algebraic laws, central limit theorem, and so on. | ||
| AI7004 | Advanced Machine Learning | |
| This course provides SVM, kernels, neural networks in supervised learning as well as clustering and dimensionality reduction in unsupervised learning. | ||
| AI7005 | Advanced Deep Learning | |
| This course provides the initializer and the optimizer for deep learning models and how to construct a deep learning model. | ||
| AI7011 | Statistical Learning Theory | |
| In this course, the students learn statistical learning theory including loss and risk. | ||
| AI7014 | Natural Language Processing | |
| This course aims to provide various topics on natural language processing such as document recognition and translation. It covers the techniques of Word2vec, Glove, LSTM, and so on. | ||
| AI7015 | Advanced Computer Vision | |
|
This course covers from basic image processing to cutting-edge technology in image and video processing domains. |
||
| AI7019 | Time Series Data Analysis | |
| In this class, the students learn the overview, implementation, and application examples of Recurrent Neural Network (RNN) which is excellent for natural language processing and time series data analysis. They also learn the structure of LSTM with an additional long-term memory concept and that of GRU, a simplified LSTM. | ||
| AI7021 | Graph Theory | |
| This course provides graph theory, Bayesian networks, sampling, and MAP reasoning which are widely used in machine learning, computer vision, and natural language processing. | ||
| AI7027 | Explainable AI | |
| Explainable AI refers to methods and techniques in the application of artificial intelligence such that the results of the solution can be understood by humans. This class teaches feature interpretation as well as rule induction. | ||
| BME704 | Engineering Mathematics | |
| This class is designed to provide basic mathematical principles and methodologies that can be employed and applied to researches in the area of biomedical engineering and electronic/computer engineering. Emphasis is given to understanding of the fundamental principles in linear algebra, and the students are encouraged to study its applications. | ||
| BME780 | Applications in Deep Learning | |
| This course aims to cover various deep learning models based on the basic principles of deep learning. In this course, students will learn unsupervised learning such as adversarial generative networks (GANs), including existing supervised learning, and implement the code based on the theory. This course aims to broaden the understanding of deep learning applications using data such as various images and signals, and to cultivate experts who can lead a new paradigm of artificial intelligence. | ||
| CSE7509 | Advanced AI Networking | |
| This course analyze the operation pattern and understand calculation pattern of artificial neural network computation processing, and acquires HW building block design, NPU architecture design, NPU programming interface, NPU compiler learning and implementation technology. | ||
| CSE7512 | Deep Learning | |
| This course studies the therory and practice from how to construct deep learning model to what is needed to learn deep learning model, such as initializer, optimizer. | ||
| CSE7513 | Advanced Linear Algebra | |
| This course studies linear programming and integer programming after learning the basic knowledge about eigenvalues, eigenvectors, orthogonality, symmetry, linear transformation and row decomposition. | ||
| CSE7521 | Advanced Probability and Statistics | |
| This course covers the mathematical fundamentals of probability and statistics theory including probabilistic models, multiple random variables, function of random variables, and random processes with special focus on discrete Markov chains. In addition, it also covers the advanced topics such as statistical estimation theory, statistical decision theory, and information theory. | ||
| CSE8303 | Digital Holography | |
| This is an advanced class for graduate students who have background knowledge in image processing and computer vision. Basic principles and state of the art methods in 3D imaging, computational imaging and processing such as multi-view stereo, RGBD based 3d reconstruction, lens-array (plenoptic camera), digital holography, coded-X imaging including corresponding 3d display technologies. Classes are composed of several lectures on the technologies, survey on cutting edge papers, student presentations and discussion. | ||
| EE7117 | Reinforcement Learning | |
| This lecture earns the concept, purpose, and components of reinforcement learning based on the Markov Decision Process (MDP). The prediction and control are studied to learn the optimal policy in Markov Decision Process(MDP) using Bellman equation. In order to train the optimal policy from the actual episodes, starting from the Monte Carlo method., Q-learning, SARSA, and Time Difference (TD) are studied. Algorithms such as DQN, AC, and A3C are learned to apply reinforcement learning to actual tasks which are non-MDP situations. | ||
| EE787 | Fundamentals of Machine Learning | |
| This course covers fundamentals of machine learning. The topics include supervised and unsupervised learning, regression and classification, a variety of loss functions, outlier rejection, overfitting and regularization, neural networks, and so on. Students will work on practical examples and numerical techniques to familiarize themselves with the covered topics. | ||
| EIC7007 | Artificial Intelligence | |
| This course covers fundamental topics on artificial intelligence, including machine learning and pattern recognition. | ||
| EIC7036 | Convergence Future Communication Colloquium I | |
| This colloquium contains a series of seminars discussing the current theoretical developments and industrial trends on convergence future communication technologies. | ||
| EIC7037 | Convergence Future Communication Colloquium II | |
| This colloquium contains a series of seminars discussing the current theoretical developments and industrial trends on convergence future communication technologies. | ||
| EIC7047 | Deep-learning programming | |
| This course contains a series of PLB type lectures on deep learning fundamentals and programming methods for deep learning. | ||
| IE727 | Special Topics in Data Science | |
| The course focuses on trends, issues, cutting-edge technologies and methodologies in Data Science. Through literature survey, it explores research trends and emerging concern. Through case study and discussion of topical issues, in addition, it seeks novel research directions making contribution to the success of Data Science application. | ||
| IE729 | Advanced Stochastic Processes | |
| Advanced topics on stochastic processes are covered. Topics include a Markov renewal process, a semi-regenerative process, Martingales and diffusion processes, | ||
| ME7121 | Introduction to AI-Robot-based Human-Machine Collaboration Technology | |
| The course aims to provide basic knowledge and various concepts used for the human-machine collaboration, particularly collaboration between the human and the AI-based robot. The Ai-based robot is the robot which utilizes the AI technique for the realization of the essential functions of the robot that includes the environment sensing, judgement, and the actuation. This course introduces the various techniques used for the AI-based robot in terms of sensing, judging and actuating. Also this course includes the basic concepts and theory and hands-on techniques required for the students who participates in ‘the AI-based Human-Machine collaboration’ program. | ||
| META7003 | Metaverse Tenology Seminar | |
| - | ||
| META7004 | Metaverse Design | |
| - | ||
| META7006 | Introduction to Mataverse | |
| - | ||
| META7011 | Avatar Behavioral Psychology | |
| This course explores the behavior of avatars and human interaction in the metaverse space, enabling students to understand the social interaction of human-avatar and avatar-avatar and the resulting social psychological phenomena in the virtual world, and to identify and solve problems. | ||
| SWCON7003 | Multi-view Geometry | |
| A basic problem in computer vision is to understand the structure of a real world scene. This course covers relevant geometric principles and how to represent objects algebraically so they can be computed and applied. We will learn epipolar geometry, fundamental matrix, camera calibration, and structure-from-motion. Recent major developments in the theory and practice of 3D scene reconstruction will be handled. | ||
| SWCON7011 | Intelligent Robotics | |
| This course introduces the science and design of robots whose programmed behavior may be described as intelligent. We will explore principles and algorithms for computation in physical world. Topics covered include behavior-based embodied artificial intelligence, kinematics and inverse kinematics, geometric reasoning, motion planning, mapping and manipulation, biologically inspired and biomimetic robotics, distributed robotics and intelligence. | ||
| SWCON7015 | Seminar on Game Analysis | |
| We will deal with the history of major games from 1970s, when the first commercially available video game was introduced. We will learn how games with purposes other than entertainment have advanced. We will categorize games after 2010 and discuss what roles will games play in modern society. | ||
| SWCON7016 | Seminar on Game Industry | |
| We will deal with past and present of game industry. We will discuss its facing problems and propose direction of the game industry. People working in game industry will be invited to give talks and discuss the relevant issues. | ||
| SWCON7018 | Brain AI | |
| The human brain is made up of neural networks, and brain-inspired AI technology refers to the process of creating artificial neural networks that work the way the human brain works. Study the neuroscience theory for the development of artificial intelligence algorithms that resemble the working principle of the brain and learn about the brain-inspired AI technology methodology. In this course, students learn about artificial intelligence models and neuroscience theories for learning, linear models, shallow neural networks, and deep learning core models. | ||
| SWCON7019 | Game & Computer Graphics Basics | |
| In this course, we learn about the theories related to computer graphics used in games. Representative technologies include procedural terrain generation, procedural texture generation, physics simulation, character animation, real-time light calculation, and deep learning-based data generation. This course focuses on basic theories. | ||
| SWCON7020 | Game & Computer Graphics Advance | |
| In this course, we learn about the theories related to computer graphics used in games. Representative technologies include procedural terrain generation, procedural texture generation, physics simulation, character animation, real-time light calculation, and deep learning-based data generation. This course focuses on advanced theories. | ||
| SWCON7021 | Robot Vision and Sensing | |
| One of the most important abilities of a mobile robot is spatial sensing. In particular, vision sensing enables robot to navigate, avoid obstacles, recognize objects by using high performance cameras. New 2D and 3D vision sensing technologies improves the robot’s safety, confidence of its motion, and eventually its productivity. In this course, we will handle various sensors such as cameras, laser scanners, IMU and GPS for spatial sensing of a robot and learn how to integrate the different sensor data in computer vision algorithms. | ||
| SWCON7022 | Technology for Extended Reality, Basics | |
| In this course, we learn the trend technologies and related theories regarding extended reality. Representative technologies include redirected walking, environment recognition, human perception in the virtual reality. This course focuses on basic theories. | ||
| SWCON7023 | Technology for Extended Reality, Advanced | |
| In this course, we learn the trend technologies and related theories regarding extended reality. Representative technologies include redirected walking, environment recognition, human perception in the virtual reality. This course focuses on basic advanced theories. | ||
| SWCON7024 | Advanced Data Science | |
| In this course, students explore the data science lifecycle, including question formulation, data collection and cleaning, exploratory data analysis and visualization, statistical inference and prediction, and decision-making. The class focuses on quantitative critical thinking and key principles and techniques needed to carry out this cycle. These include languages for transforming, querying and analyzing data; algorithms for machine learning methods including regression, classification and clustering; principles behind creating informative data visualizations; statistical concepts of measurement error and prediction; and techniques for scalable data processing. | ||
| SWCON7025 | Full Stack Deep Learning | |
| Full Stack Deep Learning helps you bridge the gap from training machine learning models to deploying artificial intelligence systems in the real world. This course teaches full-stack production deep learning: Formulating the problem and estimating project cost; Finding, cleaning, labeling, and augmenting data; Picking the right framework and compute infrastructure; Troubleshooting training and ensuring reproducibility; Deploying the model at scale. | ||
| SWCON7026 | Advanced Statistics for Data Science | |
| Statistics is used to process complex problems in the real world so that data scientists and analysts can look for meaning trends and changes. This course helps students learn about statistical analyzing tools and its accurate application. This course focuses on the statistical concepts and tools used to study the association between variables and causal inference. Key concepts include probability distributions, statistical significance, hypothesis testing, and regression. | ||
| SWCON7027 | Artificial Intelligence for Healthcare | |
| Healthcare is one of the most exciting application domains of artificial intelligence, with transformative potential in areas ranging from medical image analysis to electronic health records-based prediction and precision medicine. This course will involve a deep dive into recent advances in AI in healthcare, focusing in particular on deep learning approaches for healthcare problems. We will start from foundations of neural networks, and then study cutting-edge deep learning models in the context of a variety of healthcare data including image, text, multimodal and time-series data. In the latter part of the course, we will cover advanced topics on open challenges of integrating AI in a societal application such as healthcare, including interpretability, robustness, privacy and fairness. The course aims to provide students from diverse backgrounds with both conceptual understanding and practical grounding of cutting-edge research on AI in healthcare. | ||
| SWCON7028 | Advanced Applications of Signal Processing | |
| This course introduces characteristic, processing, and analysis methods for both one-dimensional and two-dimensional signals such as audio, active sensor data, image, and so forth. By understanding various filters, synthesis, and recognition methods that utilize temporal, spatial, and frequency data, students learn how to use them in various application systems such as autonomous vehicles and intelligent robots. | ||
| SWCON7029 | Image Recognition Using Machine Learning | |
| In this course, students learn how to make object classification, object detection, object tracking, and pose estimation using machine learning. By understanding the architectures, learning process, and analysis for models using various machine learning including deep learning, we study how to design higher performance models than the existing methods. | ||
| SWCON7030 | Open-source Software networking | |
| Understand how open source technologies are created and used. After understanding the concepts of open-source software and open-source hardware, gain the ability to use them for necessary research and development. For this purpose, computer networking, data center, and mobile communication networking are used as examples. After that, students learn to design, develop, and evaluate the experimental environment necessary for their research using open sources. | ||
| SWCON7031 | Datacenter Networking | |
| Datacenter Networking is an advanced course for undergraduate data center programming and full-stack service networking. In this course, you will learn more detailed techniques for HTTP/1.1, HTTP/2, and HTTP/3. Through this, students understand how large-scale distributed services operate on a network basis from a technical point of view. In addition, it is intended to understand the technical background for developing real-time robot communication, communication between server software for large-scale data analysis, and real-time multimedia/game server. | ||
| SWCON7032 | Technology and Practice in Human-computer Interaction | |
| This course introduces the fundamental research methods for Human-Computer Interaction (HCI) studies. Students will find, read, and review the recent HCI studies for technical aspects. Students will extensively learn the process of HCI research throughout the semester by doing their term project. | ||
| SWCON7033 | Social System Design and Analysis | |
| We are constantly connecting and communicating with numerous people online. In this course, we will explore various design elements that make up social systems and study social network theories and various social network analysis cases. Through social data collection, analysis, and insight extraction, we can develop the ability to propose more valuable system designs and strategies based on a deep understanding of people's diverse behavioral patterns. |