For more details on the courses, please refer to the Course Catalog
| Code | Course Title | Credit | Learning Time | Division | Degree | Grade | Note | Language | Availability |
|---|---|---|---|---|---|---|---|---|---|
| AIM4001 | Advanced Big Data Analytics | 3 | 6 | Major | Bachelor/Master | Artificial Intelligence | - | No | |
| This course introduces fundamental data mining and machine learning techniques for big data analytics. The emphasis in the course will be learning key techniques that are required to extract meaningful information from big data, and developing scalable data mining algorithms for big data analytics. The first half of the course will cover various supervised and unsupervised machine learning methods (theoretical analysis of the methods and their practical applications), and the last half of the course will focus on scalable graph mining techniques with special emphasis on analyzing large-scale social networks. There will be one midterm, three assignments, and the final project where students will be expected to develop scalable algorithms for collecting and analyzing big data. | |||||||||
| AIM4002 | Biomedical Artificial Intelligence | 3 | 6 | Major | Bachelor/Master | 1-4 | Artificial Intelligence | - | No |
| Biomedical research is one of the most exciting application domains of artificial intelligence, with transformative potential in areas of precision medicine. The goal of this course is to introduce the underlying concepts, methods, and the potential of intelligent systems in biomedicine. The course aims to provide students from diverse backgrounds with both conceptual understanding and practical grounding of cutting-edge research on AI in biomedicine in the areas of deep learning, bioinformatics, computational models, and data science. As a research and project-based course, student(s) will have opportunities to identify and specialize in particular AI methods, biomedical applications, and relevant tools. The course is designed to be accessible to non-quantitative majors but will require prior programming experience. | |||||||||
| 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 | Korean | Yes |
| MachineLearningisthestudyofhowtobuildcomputersystemsthatlearnfromexperience.Thiscoursewillgiveanoverviewofmanymodelsandalgorithmsusedinmodernmachinelearning,includinggeneralizedlinearmodels,multi-layerneuralnetworks,supportvectormachines,Bayesianbeliefnetworks,clustering,anddimension reduction. | |||||||||
| AIM5003 | Theory of Pattern Recognition | 3 | 6 | Major | Master/Doctor | Artificial Intelligence | - | No | |
| Thiscourse covers the basictechnologiesonprocessingandrecognitionofdigitalimagepatterns.Mainsubjectsarestatisticalpatternrecognition,supervisedlearning,lineardiscriminationfunctions,unsupervisedlearning,syntacticpatternrecognition,parsingandgrammars,graphicalsyntacticpatternrecognition,grammaticalinference,neuralpatternrecognition,andsoon | |||||||||
| 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. | |||||||||
| AIM5005 | Database Theory of applications | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| Inthiscourse,weintroducedatabasedesignmethodologyfundamentalforconstructinginformationsystemsandinvestigatepracticaldatabasedesigncasestudy.Themajorcontentsthatwillbecoveredisthefollowing:datamodelingconcepts,conceptualdesignmethodologies,viewdesignandintegration,improvingqualityofdatabaseschema,highleveldesignusingERmode,logicaldesignforrelationalmode,reverseengineering,designtheoryforrelationaldatabases,physicaldatabasedesign,etc. | |||||||||
| AIM5006 | Theory of Image Processing | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| Thisclassprovidesfundamentalknowledgeforacquisition,processing,displayofdigitalimagesignalsbystudyingsuchtopicsasmathematicalmodelingofimagesignal,sampling,spatialandtemporalresolution,humanvisualsystem,quantizationtheory,basic2Dsignalprocessing,2Dtransform,frequencyanalysis,filtering,imageenhancement,colorspace,colorprocessing,andcompressionandreconstruction.Selectedpracticalapplicationsareanalysedforbetterunderstandingofsuchtechniques. | |||||||||
| AIM5007 | Bigdata Processing Platform | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| ThiscoursecoversHadoopandHadoopEcoSystemwhichisagroupofapplicationsbasedonandworkingwithHadoop.StudentslearnHadooparchitecture,softwarestackandprincipleofitsprocesseslikemap-reduce.StudentsstudyHadoopecosystem,likeHive,hbase,Spark,scoop,flume,kafka,Azkaban,ambari,etc. | |||||||||
| AIM5008 | Special Topics in Artificial Intelligence and Simulation | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| This course deals with various topics on the integration of Artificial Intelligence techniques and simulations. AI is used in the model structure representation, model construction and management of simulation model using knowledge representation techniques. Expert systems is used to represent models which have complex state transition. This course covers various topics related to those. | |||||||||
| AIM5009 | Evolutionary Algorithm | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| Evolutionary Algorithms asoneofsoftcomputingtechniquesforintelligentsearchingproblems,thegeneticmethodologiessuchasgeneticalgorithms,evolutionaryprogramming,etc.,areintroducedwithanemphasisinengineeringperspectives.Thedetaileddescriptionofcomputerimplementationofgeneticalgorithmisalsogivenincludingselectionofgenepopulation,chromosome,crossover,mutation,etc.Withtheintroducedbackgroundmaterial,onecansolvethesearchproblemsforoptimalsolutiongivenasintelligentcontrolexamples. | |||||||||
| 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. | |||||||||
| AIM5011 | Numerical Analysis for AI | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| Thegoalofthiscourseistoenablestudentswithlittleornoprogrammingbackgroundtosolvecommoncomputationalproblemsinartificial intelligence.Matlaband/orPythonprogrammingwillbecovered,togetherwithbasicprinciplesofcomputerarchitectureandarithmetic.Basicnumericaltechniquesinnumericaldifferentiation,integration,linearalgebra,differentialequations,andstatistics,arecoveredandappliedtomathematical analysis in artificial intelligence field.Emphasiswillbeplacedonenablingstudentstousecurrentlyavailablenumericalmethodstosolveengineeringproblems. | |||||||||
| AIM5012 | Optimization Theory and applications | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| Linearprogramming,nonlinearprogramming,iterativemethodsanddynamicprogrammingarepresented,especiallyastheyrelatetooptimalcontrolproblems.DiscreteandcontinuousoptimalregulatorsarederivedfromdynamicprogrammingapproachwhichalsoleadstotheHamilton-Jacobi-BellmanEquationandtheMinimumPrinciple.Minimumenergyproblems,lineartrackingproblems,outputregulatorsandminimumtimeproblemsareconsidered. | |||||||||
| AIM5013 | Theory of Probability and Random Process | 3 | 6 | Major | Master/Doctor | 1-4 | Artificial Intelligence | - | No |
| Theaimofthiscourseistodevelopathoroughunderstandingoftheprinciplesofrandomprocessesandknowledgeofapplyingthemtosomeimportant problems.First,thebasictheoryinprobabilityandrandomprocessisintroduced,payingparticularattentiontothemultivariateGaussiandensityfunction.Then,thetheoryofrandomprocessesandtheircharacterizationbyautocorrelationandpowerspectraldensityfunctionsisdeveloped.Thetheoryisthenappliedtothedesignofoptimumlinearsystems. | |||||||||