교수자 소개
-
UNIST 최재식 교수2005~2012: 미국 일리노이 주립대학교 컴퓨터과학과 박사
1997~2004: 서울대학교 컴퓨터공학과 학사
2013~현재: 울산과학기술원 전기전자컴퓨터공학부 조교수
2013~현재: 미국 로렌스 버클리 연구소 객원연구원
2013~2013: 미국 로렌스 버클리 연구소 박사후연구원
2012~2013: 미국 일리노이 주립대학교 박사후연구원
2000~2003: 소만사 연구원
강의계획
강의목록
-
Week 01
- 1-1 Perceptron and its convergence theorem
- 1-2 Maximum Margin Principle and Soft Margin Hard Margin
- 1-3 Complexity of Linear Hypothesis and Margin Bound of Linear Classifiers
- 1-4 Linear models in Deep Neural Networks
-
Week 02: Sparse modeling
- 2-1 Overview of sparse modeling
- 2-2 Matrix decomposition
- 2-3 Regularized likelihood methods
-
Week 03: Causality
- 3-1 Introduction to Causality
- 3-2 Causal Bayesian Network
- 3-3 Temporal Causality
- 3-4 Counter-factual Inference
-
Week 04: Explainable AI
- 4-1 Overview of Explainable AI
- 4-2 Explaining decision of deep learning
- 4-3 Explaining complex machine learning models by decomposition
- 4-4 Featured research projects in Explainable AI
-
Week 05: Learning to learn
- 5-1 Meta learning
- 5-2 Few-shot learning
- 5-3 Model-Agnostic Meta-Learning
- 5-4 AutoML
-
Week 06: Methods to Predict the Future Values
- 6-1 Time series prediction
- 6-2 Stationarity of time series
- 6-3 Non-stationary time series
- 6-4 Deep learning-based model and recent development
-
Week 07: Reinforcement Learning: Self-Taught Artificial Intelligence
- 7-1 What is the reinforcement learning?
- 7-2 Approaches to reinforcement learning
- 7-3 xample: GridWorld
- 7-4 Example: CartPole