Course Information

Introduction to Intelligent Systems - Fall 2017
Instructor: Prof. Songhwai Oh (오성회)
Email: songhwai (at) snu.ac.kr
Office Hours: Friday 2:00-4:00PM
Office: Building 133 Room 405
Course Number: 430.457
Time: MW 11:00-12:15 PM
Location: Building 301 Room 103

TA-1: Hwiyeon Yoo (유휘연)
Email: hwiyeon.yoo (at) cpslab.snu.ac.kr
Office: Building 301 Room 718
Office Hours: Wednesday 2:00-3:30 PM 

TA-3: Timothy Ha (하디모데)
Email: timothy.ha (at) cpslab.snu.ac.kr
Office: Building 301 Room 718
Office Hours: Wednesday 2:00-3:30 PM 

TA-2: Yunho Choi (최윤호)
Email: yunho.choi (at) cpslab.snu.ac.kr
Office: Building 301 Room 718
Office Hours: Wednesday 2:00-3:30 PM 

TA-4: Jaegu Choy (최재구)
Email: jaegu.choy (at) cpslab.snu.ac.kr
Office: Building 301 Room 718
Office Hours: Wednesday 2:00-3:30 PM 

Course Description

This course introduces the foundations of intelligent systems, such as probabilistic modeling and inference, statistical machine learning, computer vision, and robotics, to undergraduate students. Topics include Bayesian networks, hidden Markov models, Kalman filters, Markov decision processes, linear regression, linear classification, and nonparametric models. Students will also learn about how these methods are applied to practical applications such as computer vision and robotics. Lectures will be in English.

RC Car Racing: A Navigation Challenge

홍보2.PNG DSC04467.JPG
  

Project and Announcements

Schedule

Week Reading Date Lecture Date Lecture
1 AIMA Ch. 13 9/4
  • Introduction
9/6
  • Traditional AI
2 AIMA Ch. 14.1 - 14.3 9/11
  • Review of probability
9/13
  • Bayesian networks
        9/15
  • Makeup lecture
    • Time: 5-8 PM
    • Location: 301-203
3 AIMA Ch. 14.4 - 14.5 9/18
  • Inference in Bayesian networks
9/20
  • Inference in Bayesian networks
4   9/25
  • No class
9/27
  • No class
5   10/2
  • Holiday
10/4
  • Holiday
6 AIMA Ch. 15.1 - 15.2 10/9
  • Holiday
10/11
  • Dynamic models

  • Inference in dynamic models

7 AIMA Ch. 15.3 - 15.7, Ch. 18.1 - 18.2 10/16
  • Hidden Markov models
  • Kalman filtering
10/18
  • Dynamic Bayesian networks
  • Supervised learning
        10/20
  • Makeup lecture
8 AIMA Ch. 18.3-18.4, 18.6-18.7 10/23
  • Decision trees
  • Linear regression
10/25
  • Linear classification
  • Artificial neural networks
9 AIMA Ch. 18.8 - 18.9 10/30
  • Nonparametric models
11/1
  • Support vector machines
10 AIMA Ch. 20.1 - 20.2, 20.3 - 20.4 11/6
  • Bayesian learning
11/8
  • EM algorithm
11 AIMA Ch. 16 11/13
  • Utility Theory
  • Decision networks
11/15
  • Midterm
12 AIMA Ch. 17.1 - 17.4, Ch. 21 11/20
  • Markov decision processes
  • POMDPs
11/22
  • Reinforcement learning
13  AIMA Ch. 25 11/27
  • Robotics (intro)
11/29
  • Localization and mapping
14   12/4
  • SLAM
12/6
  • Path planning
15 AIMA Ch. 24 12/11
  • Computer vision (intro)
12/13
  • Low-level vision
  • High-level vision

Textbook

  • [Required] Stuart Russell and Peter Norvig. Artificial Intelligence: A Modern Approach (3rd edition), Prentice Hall, 2009. (AIMA Website)

Topics

  • Review of probability and linear algebra
  • Probabilistic Modeling and Inference:
    • Bayesian networks, Hidden Markov models, Kalman filters
    • Markov decision processes
  • Machine Learning:
    • Linear classification, Linear regression, Learning with complete data
    • Learning with hidden variables, EM algorithm
    • Nonparametric models, Support vector machines
    • Reinforcement learning
  • Robotics:
    • Localization and mapping, Motion planning, Planning uncertain movements, Moving
    • Robotic software architectures, Application domain
  • Computer Vision:
    • Image formation, Edge detection, Texture, Optical flow, Image segmentation
    • Object recognition, Reconstructing the 3D world