메뉴 건너뛰기

http://slsp.kaist.ac.kr/xe/index.php?mid=mlt2016

Machine Learning Tutorial 2018 Program 
IEIE's Distinguished Lecturer Series for Machine Learning
날짜 시간 주제   강사
2018-08-06
월요일
09:00~11:00            
11:00~11:10        
11:10~12:00 Introduction to Machine Learning

  1. Introduction

  2. Framework for Machine Learning

  3. Maximum Likelihood, Large Margin Prediction

  4. Expectation Maximization

  5. Optimization

유창동 교수
KAIST

12:00~13:00 Lunch
13:00~13:50 Introduction to Machine Learning
13:50~14:00 Break
14:00~14:50 Introduction to Machine Learning
14:50~15:10 Break    
15:10~16:30 Monte Carlo Simulations

  1. Introduction

  2. Basics of Monte Carlo simulations

  3. Independent Monte Carlo (IMC)

  4. Sequential Monte Carlo (SMC)

  5. Markov Chain Monte Carlo (MCMC)
  6. Advances in MCMC

박태영 교수
연세대학교

16:30~16:50 Break
16:50~18:10 Monte Carlo Simulations
2018-08-07
화요일
09:00~10:20 Introduction to Nonparametric Bayesian Modeling

  1. Intro to Bayesian Modeling

  2. Dirichlet Process Prior and Its Applications

  3. Variants of Dirichlet Process Priors and Its Applications

  4. Beta Process and Its Applications

정연승 교수
KAIST
10:20~10:40 Break
10:40~12:00 Introduction to Nonparametric Bayesian Modeling
12:00~13:00 Lunch    
13:00~14:20 Online Learning/Optimization for Machine Learning

  1. Introduction: Learning as Mathematical Optimization

  2. Basic Algorithms: Gradient Descent and Stochastic Gradient Descent

  3. Generalization, Regularization and Regret Minimization

  4. Gradient Descent++: Modern Acceleration Techniques, Second Order Methods, Conditional Gradients

  5. A Taste of State-of-the-art

Prof. Elad Hazan

Princeton

14:20~14:40 Break
14:40~16:00 Online Learning/Optimization for Machine Learning
2018-08-08
수요일
09:00~10:20 Memory Networks

  1. Introduction to Memory Networks

  2. Neural Programming

  3. Applications for  Video and Text Summarization

김건희 교수
서울대학교
10:20~10:40 Break
10:40~12:00 Memory Networks
12:00~13:00 Lunch    
13:00~14:20

Using Neural Networks for Modelling and

Representing Natural Languages

  1. Basic Machine Learning Applied to Natural Language Tasks

  2. Introduction to Neural Networks

  3. Distributed Representations of Words

  4. Neural Network Based Language Models

  5. Efficient Text Classification

  6. Future Research and Open Problem

  7. Resources

Tomas Mikolov
Facebook
14:20~14:40 Break
14:40~16:00

Using Neural Networks for Modelling and

Representing Natural Languages

16:00~16:20 Break    
16:20~17:40 Bayesian Machine Learning

  1. Introduction to Bayesian Statistics

  2. Cons and Pros of Bayesian Statistics

  3. Bayesian Computations

  4. Applications to Machine Learning

김용대 교수
서울대학교
17:40~18:00 Break
18:00~19:20 Bayesian Machine Learning
2018-08-09
목요일
10:00~11:20

Policy Gradient Methods for

Reinforcement Learning

  1. Introduction
  2. DPG and DDPG

  3. TRPO and PPO

김기응 교수
KAIST
11:20~11:40 Break
11:40~13:00

Policy Gradient Methods for

Reinforcement Learning

13:00~14:00 Lunch    
14:00~15:20 Deep Learning

  1. Introduction to Deep Learning

  2. Convolutional Neural Networks

  3. Image Classification

  4. Image Captioning

  5. Recent Advances and Challenges in Deep Learning

김준모 교수
KAIST
15:20~15:40 Break
15:40~17:00 Deep Learning