Course Information

Introduction to Intelligent Systems - Fall 2016
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 201
TA: Chanho Ahn (안찬호)
Email: chanho.ahn (at) cpslab.snu.ac.kr
Office: Building 301 Room 718
TA: Nuri Kim (김누리)
Email: nuri.kim (at) cpslab.snu.ac.kr
Office: Building 301 Room 718

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.

Navigation Challenge


image_preview.jpg

Project and Announcements


Schedule


Week Reading Date Lecture Date Lecture
1 AIMA Ch. 13 9/5
  • Introduction
9/7
  • Traditional AI
  • Review of probability
2 AIMA Ch. 14.1 - 14.3 9/12
  • Bayesian networks
9/14
  • Holiday
3 AIMA Ch. 14.4 - 14.5 9/19
  • More on Bayesian networks
9/21
  • Inference in Bayesian networks
4 AIMA Ch. 15.1 - 15.3 9/26
  • Dynamic models
  • Inference in dynamic models
9/28
  • Inference in dynamic models
  • Hidden Markov models
5 AIMA Ch. 15.4 - 15.7 10/3
  • Holiday
10/5
  • Kalman filtering
  • Dynamic Bayesian networks
6 AIMA Ch. 18.1 - 18.4 10/10
  • Supervised learning
  • Decision trees
10/12
  • No class
7 AIMA Ch. 18.6 - 18.7 10/17
  • Linear regression
  • Linear classification
10/19
  • Artificial neural networks
        10/21
  • Makeup Lecture
  • Nonparametric models
    • Time: 5-8PM
    • Location: Bdlg. 301, Rm. 202
8 AIMA Ch. 18.8 - 18.9 10/24
  • Support vector machines
10/26
  • Midterm
9 AIMA Ch. 20.1 - 20.2,
   Ch. 20.3 - 20.4,
 
10/31
  • Bayesian learning
11/2
  • EM algorithm
10 AIMA Ch. 16.1-16.6,
   Ch. 17.1-17.3
11/7
  • Utility theory
  • Decision networks
11/9
  • Markov decision processes
11 AIMA Ch. 17.4,
   Ch. 21
11/14
  • POMDPs
11/16
  • Reinforcement learning
12 AIMA Ch. 25 11/21
  • Robotics (intro)
11/23
  • Localization and mapping
13   11/28
  • SLAM
11/30
  • Path planning
14 AIMA Ch. 24 12/5
  • Computer vision (intro)
12/7
  • Low-level vision
  • High-level vision
15       12/9
  • Navigation Challenge
    • Bldg. 133, Room 610
    • 9:30AM - 4:00PM

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