The course teaches the basic technique of computer programming and the basic knowledge in the computer structure, and use of the elective programming language to resolve given problems in structural programming. Based on the elective programming language, it teaches the data structure, input and output, flow control and incidental program, and by using the systematic division of problem solution and concept of module to solve the problems in numerical value field and non-numerical value field with the program experiment.

This course aims to provide an opportunity for sophomores to experience creative system design using Lego mindstorm NXT kit and URBI robot software platform. In lectures, robotic CS is introduced and various examples are demonstrated to bring out students' interests. In lab hours, students build own intelligent robot system creatively. Students are educated to integrate hardware and software designs, and make presentations at the end of semester.

This is an introductory-level course to database systems. Students learn about various models, such as E-R models, relational models, and object-oriented models; query languages such as SQL, relational calculus, and QBE; and file and indexing systems for data storage. Advanced topics, such as data inheritance, database design issues using functional and multivalued dependencies, database security, and access rights, are also covered. (Prerequisite: CS206)

Data science is an inter-disciplinary field focused on extracting knowledge from typically large data sets. This course aims at teaching basic skills in data science for undergraduate students. It covers basic probability and statistics theories required for data science; exploratory data analysis (EDA) required for understanding a given data set; and predictive analysis based on statistical or machine learning techniques. Additionally, it discusses recent big data processing techniques and various data science applications. The students will learn how to implement the methodologies using the Python language.

This is an undergraduate-level introductory course for deep learning. There have been enormous advances in the field of artificial intelligence over the past few decades, especially based on deep learning. However, it is not easy to see what frontiers the current deep learning is facing and what underlying methods are used to enable these advances. This course aims to provide an overview of traditional/emerging topics and applications in deep learning, and basic skill sets to understand/implement some of the latest algorithms. 

The course offers students a practical introduction to natural language processing with the Python programming language, helping the students to learn by example, write real programs, and grasp the value of being able to test an idea through implementation, with an extensive collection of linguistic algorithms and data structures in robust language processing software.

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. In this introductory course, we will cover various basic topics in the area including some recent supervised and unsupervised learning algorithms.

This course introduces the fundamental concepts of reinforcement learning and the basic principles of deep reinforcement learning, which combines these concepts with deep neural networks. Students will learn key algorithms such as Q-learning, Policy Gradient, and Actor-Critic, and explore advanced deep reinforcement learning techniques like DQN, A3C, and PPO. The course places a strong emphasis on programming and project-based practice, particularly in applying reinforcement learning to real-world problems. Additionally, the course provides a brief overview of the major challenges in reinforcement learning and discusses recent trends in the field.

Tremendous success of Artificial Intelligence (AI) can be attributed to two primary reasons: (1) significant advances in ML algorithms with great emphasis on Deep Learning, and (2) high-performance computing mainly fueled by hardware accelerators such as GPU and specialized software systems. This course focuses on the second reason and look at AI in the system perspective. This course will look into the entire computing stack built solely for AI, particularly Machine Learning and Deep Learning, This stack constitutes domain-specific programming interface and platforms (e.g., Tensorflow), DNN compilers (e.g., TVM), and hardware accelerators (e.g., GPU and TPU). 

The course aims at teaching students techniques from machine learning and programming languages that enable the design and implementation of a programming language for easily writing advanced probabilistic models from machine learning. We will cover a wide range of general-purpose algorithms for probabilistic inference, and discuss how these algorithms can be used to build programming languages and systems for developing models from machine learning. We will also study a mathematical foundation of those languages using tools from measure-theoretic probability theory.

This course aims to introduce the operations and applications of metaheuristic and bio-inspired algorithms, including genetic algorithm, swarm optimization, and artificial immune system. By considering diverse problems ranging from combinatorial ones to performance improvement of complex software system, students are expected to learn how to apply computational intelligence to unseen problems.

This course introduces basic concepts and design techniques of artificial intelligence, and later deals with knowledge representation and inference techniques. Students are to design, implement, and train knowledge-based systems.

Graphs are fundamental tools for modeling relationships between objects, enabling us to model diverse real-world problems and data. Graph machine learning and graph mining techniques are utilized in many modern AI and big data analytics domains. This course introduces various graph-based machine learning and mining techniques, including graph neural networks (applying deep learning ideas to graphs), knowledge graphs (representing human knowledge as graphs), graph representation learning (converting graphs into feature vectors), random walks and centrality measures on graphs, graph clustering, and graph anomaly detection. Also, this course introduces how these techniques are applied in information retrieval, natural language understanding, computer vision & graphics, robotics, and bioinformatics.

This course will introduce the essential techniques of text mining, understand as the process of deriving high-quality information from unstructured text. The techniques include: the process of analyzing and structuring the input text with natural language processing, deriving patterns with machine learning, and evaluating and interpreting the output. The course will cover some typical text mining tasks such as text categorization, text clustering, document summarization, and relation discovery between entities.

This course will cover important problems and concepts in natural language processing and the
machine learning models used in those problems. Students will learn the theory and practice of ML
methods for NLP, read and conduct research based on latest research publications.

This course will introduce students to the basics of embodied intelligence called intelligent robotics. The course aims to study the fundamental concepts in intelligent robotic system that can sense, plan, and act in the world. To do that, we will discuss 1) the basic concepts, such as control, kinematics, in traditional robotics and 2) state-of-the-art technologies, such as task-and-motion planning and machine learning theories, toward intelligent robotic system. The course will include a brief review of basic tools, such as Robot Operating System (ROS), and also overview contemporary techniques. It will also include individual exercise and final (individual/team) projects.

3D Data are widely used in many applications in computer vision, computer graphics, and robotic. In this course, we will cover the recent advances in machine learning techniques for processing and analyzing 3D data and discuss the remaining challenges. Most of the course material will be less-than 5-year-old research papers in several sub-fields including Computer Vision, Computer Graphics, and Machine Learning. The course will be project-oriented (no exam, no paper-and-pencil homework, but easy programming assignments) and consist of seminar-style reading group presentations.

In this course, students will learn the basic principles and techniques of image processing. Expanding the foundations of image processing, they will learn 3-dimensional image processing from camera images and also techniques for deep learning-based image understanding, combined with artificial intelligence. To this end, the curriculum of this course consists of three parts: (1) the basic principles and understanding of image processing, (2) the basic principles and understanding of 3D image processing, and (3) the basic principles and understanding of image processing using artificial intelligence. Students learn and experience basic principles for computer vision and various image processing applications based on the deep understanding of computer vision.

The course studies concepts, theories and state-of-the-art methods for visual learning and recognition. This module is unique focusing on a broader set of machine learning, for computer vision, in an optimisation perspective. 

The ability to handle big data and statistically analyse them is crucial for data scientists. This course covers social data basics and tools to handle, analyze, and visualize such data via utilizing key analysis packages in R.

Classical artificial intelligence algorithms and introduction to machine learning based on probability and statistics.

The goal of this course is to provide students with state-of-the-art technologies in intelligent robotics. Major topics include sensing, path planning, and navigation, as well as artificial intelligence and neural networks for robotics.

As a typical application of symbolic AI machine translation (M.T) addresses the major issues involving computational linguistics, rules base, and more fundamentally knowledge representation and inference. In this regard, the goal of the course is to provide students with first-hand experience with a real AI problem. The topics include application of M.T., basic problems in M.T., and classical approaches to the problems.

The goal of this course is to provide students with theory and application of computer vision. Major topics include digital image fundamentals, binary vision, gray-level vision, 3-D vision, motion detection and analysis, computer vision system hardware and architecture, CAD-based vision, knowledge-based vision, neural-network-based vision.

This course focuses on universal models for languages, especially English and Korean. For computational study, issues on knowledge representation, generalized explanation on linguistic phenomena are discussed. When these models are applied to natural language processing, properties needed for computational models and their implementation methodologies are studied.

The goal of this course is to learn the basics of how to use sensor data for designing intelligent IoT services. The course covers the entire process of IoT data science for ubiquitous computing: i.e., data collection, pre-processing, feature extraction, and machine learning modeling. Mobile, wearable, and smart sensors will be used, and the types of sensor data covered include motion (e.g., vibration/acceleration, GPS), physiological signals (e.g., heart rate, skin temperature), and interaction data (e.g., app usage). Students will learn the basic digital signal processing and feature extraction techniques. Basic machine learning techniques (e.g., clustering, supervised learning, time-series learning, and deep learning) will be reviewed, and students will master these techniques with in-class practices with Google Co-lab and IoT devices. A final mini-project will help students to apply the techniques learned in the class to solve real-world IoT data science problems. 

Recent progress in AI technologies and research have raised concerns about data privacy and protection, misuse of AI to harm people and society, bias in data and trained models, and AI divide that benefits the rich people and nations more than the poor. It is thus very important to learn about the ethical issues of AI including bias, fairness, privacy, trust, interpretability, and societal impact.

This course will introduce graduate students to the emerging area of robot learning and interaction toward human-centered robotics. The course overviews each robotic learning and interaction areas including learning from demonstration (LfD), (inverse) reinforcement learning (RL), natural language interaction, interactive perception, etc. We will then review the state-of-the-art technologies and exercise a part of technologies using simulated robotic manipulators via Robot Operating System (ROS). Finally, we will exercise the learned techniques via final individual/team projects. 

In this class we will discuss various techniques of motion and path planning for various robots. We go over various classic techniques such as visibility graphs and cell decomposition. In particular, we will study probabilistic techniques that have been used for a wide variety of robots and extensively investigated in recent years.

In this class we will discuss various techniques related to image/video search. Especially, we will go over deep learning image/video features, their indexing data structures, and runtime query algorithms. We will also study recent learning based techniques that can handle various multi-modal data in addition to looking into novel applications of them.

The goal of this course is to study the theory, algorithms and methods that underlie distributed database management systems.

This course will cover advanced and state-of-the-art machine learning such as graphical models, Bayesian inference, and nonparametric models.

This course covers reinforcement learning, which is one of the core research areas in machine learning and artificial intelligence. Reinforcement learning has various applications, such as robot navigation/control, intelligent user interfaces, and network routing. Students will be able to understand the fundamental concepts, and capture the recent research trends.

The goal of this course is to provide students with recent theory of AI and its application. It covers information representation. heuristic search, logic and logic language, robot planning, AI languages, expert system, distributed AI system, uncertainty problem and so on.