For more details on the courses, please refer to the Course Catalog
| Code | Course Title | Credit | Learning Time | Division | Degree | Grade | Note | Language | Availability |
|---|---|---|---|---|---|---|---|---|---|
| ESW4006 | Information Visualization | 3 | 6 | Major | Bachelor/Master | Computer Science and Engineering | Korean | Yes | |
| With the advances in data storing and processing technologies, the size of data humans confront is increasing at an unprecedented rate. Despite the ever-increasing data size, our perceptual and cognitive abilities stay relatively unchanged, leading to an information gap between humans and data. Information visualization provides one means of addressing such information overload, as well-designed visual representations can assist our perceptual and cognitive abilities to understand, analyze, and memorize the data. In this course, students will learn to 1) design, evaluate, and critique visualization designs, 2) comprehend the characteristics of humans' perception that underpin visualization, 3) understand novel visualization and interaction techniques, and 4) implement interactive data visualizations. The topics of this course will include but not limited to: - Foundations of Information Visualization, Exploratory Data Analysis (EDA), Visual Analytics - Data and Task Abstraction - Mark, Channel, Color, Perception, Interaction, and Animation - Tables, Maps, Networks, Text, and Uncertainty - Visualization for Large-scale and High-dimensional Data - Visualization for the Explainability and Trustworthiness of Machine Learning Methods | |||||||||
| ESW4014 | Principles of Reinforcement Learning | 3 | 6 | Major | Bachelor/Master | Computer Science and Engineering | Korean | Yes | |
| In this course, students learn the basic theory algorithm of Reinforcement Learning (RL) to find the optimal policy for a given environment. From basic reinforcement learning theories such as Markov Decision Process, Planning, and Q-learning to deep neural network-based reinforcement algorithms such as Value Function Approximations and Policy Gradient Methods. In addition, Model-based RL through estimating environments, Exploitation & Exploration Trade-off, and Inverse RL that mimics the behavior of experts are also covered. Basic knowledge of data structures, algorithms and machine learning is required to take this course. | |||||||||
| ESW4024 | Introduction to Recommender Systems | 3 | 6 | Major | Bachelor/Master | 1-4 | Computer Science and Engineering | - | No |
| Recommendation systems aim to use the user's click/purchase history and the content information of items to predict the user's hidden preferences and to provide items that the user would like to prefer. The recommendation systems have been widely used in various domains, such as Web applications, online streaming services, and E-Commerce. This course covers the basic concepts and implementations of various recommender models. We deal with collaborative filtering (CF), which utilizes only user history, and content-based filtering (CBF), which utilizes the similarity between items. Specifically, CF models include conventional neighbor-based and model-based methods for linear and non-linear models using deep neural networks. We also investigate factorization machines and sequential-based recommender models. Furthermore, we implement various recommender models and evaluate them. | |||||||||
| ESW5012 | Topics in Real-Time Systems for Software Platforms | 3 | 6 | Major | Master/Doctor | 1-4 | Computer Science and Engineering | English | Yes |
| This course studies classic real-time systems' theories, and then investigates the-state-of-the-art issues of real-time systems towards supporting software platforms. First, fundamental scheduling theories are covered, including scheduling for the basic real-time task model in uniprocessor/ multiprocessor/cluster platforms, as well as that for the fork-join model and synchronization. Based on the theoretical background, up-to-date papers for real-time systems are studied so as to support software platforms. | |||||||||
| ESW5014 | Advanced Topics in Computer Graphics | 3 | 6 | Major | Master/Doctor | 1-4 | Computer Science and Engineering | - | No |
| This course covers fundamental theories, advanced techniques, and practice in computer graphics. The theories covered in this course include images, geometry, modeling, transformation, projection, shading, texture mapping, ray tracing, global illumination, and special effects. The course also includes practical techniques to implement the theories using graphics processors. | |||||||||
| ESW5023 | Text Mining and Analytics | 3 | 6 | Major | Master/Doctor | Computer Science and Engineering | - | No | |
| Text mining and analytics is the process of discovering hidden knowledge from text data. Basically, text mining involves text categorization, text clustering, concept/entity extraction, sentiment analysis, document summarization, and entity relation modeling. Text analysis involves information retrieval, lexical analysis for word frequency distributions, and information extraction. The essential goal is to turn text into data for analysis via natural language processing (NLP) and analytical methods. In this course, we will cover the major techniques for text mining and analytics to discover interesting patterns and to extract useful knowledge, based on statistical approaches. We will also implement text mining techniques using Python library. For prerequisite courses, I strongly recommend that you take basic computer programming, data structures, algorithms, data mining, and machine learning. | |||||||||
| ESW5024 | Advanced Data Analysis | 3 | 6 | Major | Master/Doctor | Computer Science and Engineering | English | Yes | |
| This class is to explore the most common methods used in the field of data analysis and statistical modeling to analyze real-world data, i.e., data summaries, visualization, prediction, and as tools for scientific inference and causal data analysis. The course deals with benchmark data that displays non-linear patterns, frequency data, count data, and longitudinal data. Assuming that students are familiar with basic probability and mathematical statistics, the course covers several topics related to VC theory, convergence, point and interval estimation, maximum likelihood, hypothesis testing, data reduction, Bayesian inference, nonparametric statistics, and bootstrap resampling, dependent data analysis, and causal inference. By completing the course, students with a data analysis problem will be able to select the appropriate statistical/analytical methods to critically evaluate the resulting statistical models, and report the results. The course's primary goal is to familiarize graduate students with the modern methods of data analysis and help them to choose the right method for the research job at hand (rather than distorting the problem to fit the methods you happen to know). This is crucial for having high-quality research results. | |||||||||
| ESW5048 | Trustworthy Machine Learning | 3 | 6 | Major | Master/Doctor | 1-4 | Computer Science and Engineering | English | Yes |
| As machine learning (ML) and deep learning (DL) systems are increasingly implemented in real-world applications to improve our lives, it is essential to guarantee that these systems exhibit appropriate and trustworthy behavior. Researchers and practitioners are increasingly interested in developing and deploying ML models and algorithms that are not just accurate, but also explainable, fair, privacy-preserving, causal, and robust. The course helps students learn about current efforts to develop trustworthy machine learning models. The course covers a variety of developing research issues relating to model fairness and transparency, ML/DL explainability, and security and privacy of ML models. The majority of the course contnent and readings will include of both seminal and recent publications in top venues. This course demands a solid understanding of machine learning, particularly deep learning and Python programming, in order to comprehend the course material. | |||||||||
| ESW5049 | Advanced Topics in Machine Learning | 3 | 6 | Major | Master/Doctor | Computer Science and Engineering | English | Yes | |
| This course is designed for graduate students who have a foundational understanding of machine learning and are looking to delve deeper into advanced concepts and recent ML-based applications. The course focus on recent advances in machine learning and goes in depth on selected topics and methods within machine learning and their applications, including generative models, probabilistic models and Bayesian methods, networks optimization algorithms, multimodal Learning, multitask learning, ensemble learning, attention mechanisms and transformers, interpretable models, graph neural networks, and adversarial learning. By covering these topics, the course also covers applications in domains such as computer vision, natural language processing, and biomedical. By completing this course, the student should be able to critically evaluate machine learning literature and current research trends. The course develops the ability to design, implement, and assess machine learning solutions for real-world applications. | |||||||||
| SUP5001 | Deep Neural Networks: Theory and Applications | 3 | 6 | Major | Master/Doctor | 1-4 | Superintelligence Engineering | - | No |
| This course covers deep learning based on artificial neural network which is advanced on various industrial. This course, especially, give students basic understanding of modern neural networks and their applications in computer vision and natural language understanding. Students learn about Convuloutional networks, RNNs, LSTM, Dropout and more. This course introduceds the major technology trens driving Deep Learning. | |||||||||
| SUP5003 | Machine Learning Algorithms and Applications | 3 | 6 | Major | Master/Doctor | 1-4 | Superintelligence Engineering | English | Yes |
| This course introduces various machine learning models for supervised & unsupervised learning, in order to motivate students who are new to machine learning. In addition, it provides assignments for hands-on practice using scikit-learn (machine learning library operating on python), so that students have chance to apply machine learning models to particular problems with real-world datasets. Regarding supervised learning, we begin with linear regression and introduce ridge regression where L2 regularization method is applied to alleviate over-fitting. Logistic regression is introduced, which is a popular tool for binary classification. k-nearest classifier and Naive Bayes classifier with its application to text classification are also introduced. Tree-based models such as CART is introduced, ensemble of trees, including random forest and boosting are covered. Finally support vector machines, which are large-margin classifiers, are introduced to complete the supervised learning topic. Regarding unsupervised learning, we introduce two clustering methods, including k-means clustering and mixture of Gaussians. For dimensionality reduction, we provide principal component analysis (PCA), nonnegative matrix factorization (NMF), and stochastic neighborhood embedding (SNE). | |||||||||
| SUP5006 | Mathematics for Machine Learning | 3 | 6 | Major | Master/Doctor | 1-4 | Superintelligence Engineering | Korean | Yes |
| This course introduces a few mathematics which is essential for machine learning, to help students to better understand various machine learning models. Regarding linear algebra, we begin with vectors and matrices and cover linear algebraic equations, inner product, vector norms, orthogonal projection. We also introduce a popular matrix decomposition, like SVD and explain how such method is used in machine learning. Regarding probability and distributions, we introduce random variables, expected values, and two exemplar distributions, including Gaussian for continuous random variables and Bernoulli for bianry random variables. Regarding parameter estimation, we introduce maxinum likelihood and MAP estimation methods. Regarding information theory, we introduce entropy, mutual information, KL-divergence, and explain how these are used in machine learning. Regarding continuous optimization, we begin with vector calculus, and introduce two iterative methods such as gradient descdent/ascent, Newton’s method. Finally we conclude this course, having a look at a few machine learning models to understand how relevant mathematics are utilized in machine learning. | |||||||||
| SUP5008 | System Intelligence | 3 | 6 | Major | Master/Doctor | Superintelligence Engineering | Korean | Yes | |
| With the rapid development of AI and broad adoption of AI applications, it is required to have the system structure that can optimally support model learning and inference at scale. This application and system technology is also evolving in the direction of automation, efficiency, and optimization, leveraging data-driven machine learning technology. Based on interdisciplinary works on systems, networks, and machine learning, this course discusses (1) various AI-based methods to address system problems and (2) network and system configuration techniques required to apply AI to real-world problems. The schedule for the course is as follows. ● Weeks 1-5: Machine learning for system problem solving (e.g., reinforcement learning, meta learning, imitation learning, self-supervised learning.) ● Weeks 6-10: Machine learning-based approaches to system problems (e.g., automation, resource management, scheduling.) ● Week 11-15: System structures for real-world AI systems (e.g., distributed learning platform, model compression, acceleration, etc.) | |||||||||