Go to login Go to sub menu Go to text

Course summary

  • Type MOOC course
  • Period Always open
  • Learning Time 18hr
  • Course approval method Automatic approval
  • Certificate Issue Online
Copy URL BAND Facebook Twitter
http://kooc.kaist.ac.kr/aiml-adv3
둘러보기
Thumb up 114 Learner 451

인공지능 및 기계학습 심화3

KAIST 산업및시스템공학과 문일철 교수님

Instructor Introduction

  • KAIST 산업및시스템공학과 문일철 교수님

    KAIST 산업및시스템공학과 부교수
    KAIST 김재철AI대학원 겸임교수
    KAIST 항공우주공학과 겸임교수
    KAIST 안보융합연구원 겸임교수
    한국인공지능학회 교육이사

Lecture plan

★강의목록
  1. CHAPTER 1 : Basic of GAN
    1. Basic of GAN: Implicit Distribution
    1. Basic of GAN: Overview and Notations
    1. Basic of GAN: Formalization
    1. Basic of GAN: Analogy
    1. Basic of GAN: Quiz 1
  2. CHAPTER 2 : GAN Objectives and Structures
    1. GAN Objectives and Structures: Loss Function
    1. GAN Objectives and Structures: Jensen-Shannon Divergence
    1. GAN Objectives and Structures: Training
    1. GAN Objectives and Structures: Theoretical Results
    1. GAN Objectives and Structures: Quiz 2
  3. CHAPTER 3 : Mode Collapse of GAN
    1. Mode Collapse of GAN: Introduction
    1. Mode Collapse of GAN: Unrolled GAN(1)
    1. Mode Collapse of GAN: Unrolled GAN(2)
    1. Mode Collapse of GAN: Effects of Mode Collapsing by Unrolled GAN
    1. Mode Collapse of GAN: Quiz 3
  4. CHAPTER 4 : Latent and Conditional Modeling on GAN
    1. Latent and Conditional Modeling on GAN: cGAN
    1. Latent and Conditional Modeling on GAN: Adding Latent Variable to GAN
    1. Latent and Conditional Modeling on GAN: InfoGAN(1)
    1. Latent and Conditional Modeling on GAN: InfoGAN(2)
    1. Latent and Conditional Modeling on GAN: cGAN vs InfoGAN
    1. Latent and Conditional Modeling on GAN: Quiz 4
  5. CHAPTER 5 : f-GAN
    1. f-GAN: Generalize Divergence
    1. f-GAN: Convex Conjugate Function
    1. f-GAN: f-divergence
    1. f GAN: Optimal Tau of Fenchel Conjugate
    1. f-GAN: Variational Divergence Minimization(1)
    1. f-GAN: Variational Divergence Minimization(2)
    1. f-GAN: Difference of Two Probability Distributions
    1. f-GAN : Quiz 5
  6. CHAPTER 6 : GAN with IPM
    1. GAN with IPM: Definitions and Types
    1. GAN with IPM: GAN+MMD(1)
    1. GAN with IPM: GAN+MMD(2)
    1. GAN with IPM: Parallel Line Density Example
    1. GAN with IPM: Wasserstein Distance
    1. GAN with IPM: Kantorovich-Rubinstein Duality
    1. GAN with IPM: Wasserstein as Primal LP
    1. GAN with IPM: Wasserstein as Dual LP
    1. GAN with IPM: Property of Dual LP on Wasserstein Distance
    1. GAN with IPM: Lipschitz Continuity
    1. GAN with IPM: Dual Problem of Wasserstein Distance
    1. GAN with IPM: Kantorovich-Rubinstein Duality and Wassertein GAN
    1. GAN with IPM: Quiz 6
  7. ★강의 수강 후 의견을 부탁드리겠습니다.★
    1. 교수님 강의에 대한 별점을 매겨주세요. 여러분의 의견이 많은 도움이 됩니다:D