4190.408 Artificial Intelligence (Spring 2018)
- Instructor: Prof. Byoung-Tak Zhang
- TA: Seong-ho Choi, Seung-jae Jung
- Contact: ta.4ai18s@gmail.com
- Classroom: 302-107
- Time: Tue & Thu 11:00–12:15
Course Objectives
- To study a wide range of artificial intelligence theory, techniques, and systems about machines that behave and think like people.
- To understand concepts, models, and algorithms to develop intelligent agents such as navigation, reasoning, planning, knowledge representation, decision making, learning, visual and language.
- To learn and practice key technologies of artificial intelligence such as empirical search, Bayesian network, Hidden Markov network, and reinforcement learning.
Textbooks
- Artificial Intelligence: A Modern Approach — Russell & Norvig — Pearson — 2010
References
- 장병탁, 장교수의 딥러닝, 홍릉과학출판사, 2017
Grading Policy
| 구분 | 비율 |
|---|---|
| Mid / Final Terms | 60% |
| Project | 20% |
| Homework & Practice | 20% |
Projects
- Project 1: Analysis of AlphaGo
- Project 2: Hidden Markov Models
Course Schedule
Week 1 (3/6, 3/8)
- History (Ch. 1 Introduction)
- Agents (Ch. 2 Intelligent Agents)
Week 2 (3/13, 3/15)
- Search 1 (Ch. 3 Solving Problems by Searching)
- Search 2 (Ch. 4 Beyond Classical Search)
Week 3 (3/20, 3/22)
- Search 3 (Ch. 5 Adversarial Search)
- Practice Session 1 · Project 1 Announcement
Week 4 (3/27, 3/29)
- Logical Reasoning 1 (Ch. 7 Logical Agents)
- Logical Reasoning 2 (Ch. 8 First-Order Logic, Ch. 9 Inference in First-Order Logic)
Week 5 (4/3, 4/5)
- Practice Session 2
- Probabilistic Reasoning 1 (Ch. 13 Quantifying Uncertainty)
Week 6 (4/10, 4/12)
- Probabilistic Reasoning 2 (Ch. 14 Bayesian Networks)
- Probabilistic Reasoning 3 (Ch. 14 Exact Inference in BNs)
Week 7 (4/17, 4/19)
- Probabilistic Reasoning 4 (Ch. 14 Approximate Inference in BNs)
- Review and Discussion
Week 8 (4/24, 4/26)
- Mid-term Exam
- Practice Session 3 (Hidden Markov Models) · Project 2 Announcement
Week 9 (5/1, 5/3)
- Temporal Reasoning 1 (Ch. 15 HMM)
- Temporal Reasoning 2 (Ch. 15 Kalman Filters, DBN, Particle Filters)
Week 10 (5/8, 5/10)
- Temporal Reasoning 3 (Ch. 15 Dynamic Bayesian Networks)
- Learning Probabilistic Models 1 (Ch. 20)
Week 11 (5/15, 5/17)
- Neural Networks (Ch. 18.7 Artificial Neural Networks)
- Neural Networks (continued)
Week 12 (5/22, 5/24)
- Holiday
- Practice Session 4
Week 13 (5/29, 5/31)
- Natural Language (Ch. 22–23 Natural Language Processing)
- Vision (Ch. 24 Perception)
Week 14 (6/5, 6/7)
- Robotics (Ch. 25 Robotics)
- Final Exam
Week 15 (6/12, 6/14)
- Project 2 Poster Presentation
- Future of AI (Discussion)