For more details on the courses, please refer to the Course Catalog
| Code | Course Title | Credit | Learning Time | Division | Degree | Grade | Note | Language | Availability |
|---|---|---|---|---|---|---|---|---|---|
| AIM4003 | Natural Language Processing Fundamentals | 3 | 6 | Major | Bachelor/Master | 1-4 | Artificial Intelligence | Korean | Yes |
| his course covers the overall content of theories and techniques for analyzing and generating natural languages. This course deals with NLP overview, text corpus lexical resources, preprocessing, POS tagging, text vectorization, document classification, syntax analysis, semantic analysis, word embeddings, summarization, deep learning based language models. After taking this course, students are expected to implement programs to solve text problems. To take this course, students are required to have sufficient knowledge in machine learning, deep learning, and Python programming. | |||||||||
| AIM5001 | Theories of Artificial Intelligence | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | Korean | Yes | |
| In this course students will learn the fundamental algorithms of Aritificial Intelligence including the problem solving techniques, search algorithms, logical agents, knowledge representation, inference, and planning. After taking the course, students are expected to implement the algorithms using computer programming languages. | |||||||||
| AIM5002 | Theory of Machine Learning | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| MachineLearningisthestudyofhowtobuildcomputersystemsthatlearnfromexperience.Thiscoursewillgiveanoverviewofmanymodelsandalgorithmsusedinmodernmachinelearning,includinggeneralizedlinearmodels,multi-layerneuralnetworks,supportvectormachines,Bayesianbeliefnetworks,clustering,anddimension reduction. | |||||||||
| AIM5004 | Deep Neural Networks | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | - | No | |
| In this class, we will cover the following state-of-the-art deep learning techniques such as linear classification, feedforward deep neural networks (DNNs), various regularization and optimization for DNNs, convolutional neural networks (CNNs), recurrent neural networks (RNN), attention mechanism, generative deep models (VAE, GAN), visualization and explanation. | |||||||||
| AIM5010 | Advanced Reinforcement Learning | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| Reinforcement learning is one powerful paradigm for an enormous range of tasks, including robotics, game playing, consumer modeling and healthcare. In this class, we will provide a solid introduction to the field of reinforcement learning including Markov decision process, planning by dynamic programming, model-free prediction, model-free control, value function approximation, policy gradient methods, integrating learning and planning, exploration and exploitation. | |||||||||
| AIM5020 | Theory of Computer Vision | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| ThislessondiscussesbasictechnologiesonInput,processinganddisplayingofvisualsignals.Mainsubjectsareimagealgebra,imageenhancementtechniques,edgedetection,thresholding,thinningandskeletonizing,morphologicaltransforms,linearimagetransforms,patternmatchingandshapedetection,imagefeaturesanddescriptors,deepneuralnetworks,andsoon. | |||||||||
| AIM5021 | Natural Language Processing Theory and applications | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| Naturallanguageprocessing(NLP)isoneofthemostimportanttechnologiesoftheinformationage.Understandingcomplexlanguageutterancesisalsoacrucialpartofartificialintelligence.TherearealargevarietyofunderlyingtasksandmachinelearningmodelsbehindNLPapplications.Inthiscoursestudentswilllearntoimplement,train,debug,visualizeandinventtheirownneuralnetworkmodels.Thecourseprovidesathoroughintroductiontocutting-edgeresearchindeeplearningappliedtoNLP.thiscoursewillcoverwordvectorrepresentations,window-basedneuralnetworks,recurrentneuralnetworks,long-short-term-memorymodels,recursiveneuralnetworks,convolutionalneuralnetworksaswellassomerecentmodelsinvolvingamemorycomponent. | |||||||||
| AIM5024 | Recommendation Systems | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| A recommendation system is the information filtering system that seeks to predict the rating or preference that a user would give to a target item. In this course, we will cover non-personalized recommender systems, content-based and collaborative techniques. We also cover nearest neighborhood methods and matrix factorization methods. Lastly, we will address the recent advances in recommender systems using deep neural networks. | |||||||||
| AIM5029 | AI Colloquium | 1 | 2 | Major | Master/Doctor | Artificial Intelligence | - | No | |
| Thisclassprovidesbroadknowledgeaboutmanyfieldsofinformationtechnology.VarioussubjectsareselectedwhicharecurrentlyhotissuesinArtificial Intelligence andinvitedtalksaregivenabouttheselectedsubjects. | |||||||||
| 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. | |||||||||
| AIM5056 | Machine learning with Graphs | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | - | No | |
| 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. | |||||||||
| AIM5070 | Spoken Language Processing | 3 | 6 | Major | Master/Doctor | 1-8 | Artificial Intelligence | Korean | Yes |
| This course provides how recent AI developments are applied to speech processing, building on conceptual and mathematical foundations of speech signals. Core topics are speech recognition (STT) and speech synthesis (TTS), including essential natural language processing techniques required for speech AI. The course also explores how speech AI is evolving in the era of large language models (LLMs). | |||||||||
| AIM5071 | Advanced Topics in Multimodal Artificial Intelligence | 3 | 6 | Major | Master/Doctor | 1-8 | Artificial Intelligence | Korean | Yes |
| This course provides a broad exploration of modern multimodal AI, covering theoretical foundations, recent research trends, and practical applications. In particular, the course discusses how text-based language models integrate with vision, audio, robotics, and other modalities. The course also discusses multimodal understanding and generation, representation leraning, multimodal alignment and verification methods, reasoning, and hallucination mitigation techniques. | |||||||||
| AIM5072 | Efficient Deep Learning and Optimization | 3 | 6 | Major | Master/Doctor | 1-8 | Artificial Intelligence | - | No |
| This course provides an in-depth exploration of optimization techniques that enable efficient training and inference of deep learning models. Starting from practical constraints, the topic includes model-level optimzation methods (pruning, quantization, etc.) and algorithm-level optimization methods (dynamic selection, diffusion simplification, etc.). Finaly, the course discusses recent LLM-oriented optimization methods. | |||||||||
| AIM5073 | Self-Supervised Learning | 3 | 6 | Major | Master/Doctor | 1-8 | Artificial Intelligence | - | No |
| This graduate-level course covers the fundamentals and recent advances in self-supervised learning (SSL), a methodology for learning representations from data without explicit labels. Self-supervised learning has become a core paradigm for training large-scale models across various domains, including computer vision, natural language processing, speech, and time-series analysis. The goal of this course is to provide a systematic understanding of these developments. Students will read, present, and discuss recent research papers each week to gain insight into current trends. In addition, they will write a technical report on a selected topic, analyzing the strengths and weaknesses of SSL methods, their applications, and future research directions. This course is suitable for students who wish to develop a deep understanding of representation learning in deep neural networks and build foundational skills that can be extended to real research problems. | |||||||||