This graduate course is an introductory course on deep learning for computer vision by which students will learn the fundamentals of image processing techniques based on artificial intelligence. The goal of this course is to understand not only deep neural networks including convolutional neural networks but also their applications to visual recognition tasks such as image classification, localization, and detection. The students will perform term projects, where they implement their own networks using deep learning libraries for their choices of computer vision problems.

This graduate course addresses such emerging application problems of computer vision as image inpainting, super resolution, human pose estimation, 2D-to-3D reconstruction, and text-to-image generation, and practice them through programming. Students will learn the state-of-the-arts deep learning technologies such as transformer, graph neural network, and DALL·E. This course requires students to complete one of the following subjects as prerequisite: Deep Learning for Computer Vision, Machine Learning for AI, Advanced Big Data Processing, or other subjects recognized as equivalent.

In this graduate course, students will learn about the fundamentals of machine learning which is the core for artificial intelligence (AI) in the era of the Fourth Industrial Revolution. The course will address the essential theories and ideas of machine learning, and aim to lay the foundation of understanding such state-of-the-arts AI technologies as deep learning. Concretely, this lecture will cover mathematical backgrounds for machine learning, primary concepts of machine learning, regression, clustering, supervised and unsupervised learning, Bayesian models, neural networks, and reinforcement learning.

In this graduate course, students will study selected special topics of the fields of artificial Intelligence to keep up with the latest AI technologies and trends which are rapidly advancing. This lecture aims to improve students' capabilities of analyzing research papers and having discussion to understand the state-of-the-art artificial intelligence technologies and apply them for a diversity of scientific and engineering projects.

This graduate course aims to understand the basic concepts and data formats for bioinformatics, including DNA sequencing and database, and to practice such data mining problems of bioinformatics as classification and clustering using machine learning. Concretely, we will have essential capabilities to handle bio data and make use of advanced data mining algorithms to analyze bio data.

This graduate course aims to understand the state-of-the-art bioinformatics technologies especially focusing on deep learning and write down a comprehensive report through collaborative/multi-disciplinary study and discussion among students whose majors are either computer science or life science.

This graduate course will address the essential theories and ideas of machine learning which underlies AI technologies, and aim to lay the foundation of understanding such state-of-the-arts AI technologies as deep learning. Concretely, we will cover mathematical backgrounds for machine learning, primary concepts of machine learning, regression, supervised and unsupervised learning, artificial neural networks, and deep neural networks.

This graduate course deals deeply with student's own research subjects in the field of information and communications including machine learning and computer vision. Students will learn strategies to define engineering problems, suggest ideas for resolving the problems, implement their ideas and evaluate their implementations. Students will ultimately practice writing a paper and publishing it. 

The goal of this course is to understand the basic theories and concepts of machine learning and practice them through programming. Students will first learn Python programming as well as basic mathematics including linear algebra, probability, and information theory. The main topics of this course cover linear regression, logistic regression, gradient descent optimization, support vector machine, decision tree, random forest, principal component analysis, multilayer perceptron, hyperparameter tuning, and regularization.

The goal of this course is to understand the basic theories and concepts of image processing and practice them through programming. Students will learn Python programming, image filtering, edge detection, geometric transforms, morphological operations, and Fourier transform. Especially, they will be also introduced basic models of machine learning to solve advanced problems of image processing such as image classification and object detection.

The goal of this course is to improve synthetic abilities of problem solving in the industrial field of information and communications (including artificial intelligence, image processing, mobile communication, self-driving cars, and drone control). Students can experience the overall procedures for creative engineering design including topic choice, project planning, conceptual/detailed design, as well as experimental planning, making prototype, evaluation and improvement, reporting, and finally creating a portfolio. Through the advisor's guidance and teamwork, students can significantly improve their capabilities for problem solving and integrating knowledges from different specialties, and for reporting and presenting.

Mathematics is essential to understand theories and applications for engineering. The main goal of this course is to improve strategies of problem solving using mathematical tools in the field of electronic engineering and information technologies. The topics of this course include ordinary differential equations, Laplace transform, vector spaces, arrays, linear (differential) equations, linear algebra, and Fourier analysis. Students can finally learn how to build mathematical models for problem solving.

Coding is fundamental for information and communication technologies in the fourth industrial revolution. This course provides a well-organized program for students to learn basic and advanced knowledge of the C language, and improve practical coding ability and skills, so that they can carry out software development by themselves.