Course Information

Introduction to Intelligent Systems - Fall 2014
Instructor: Prof. Songhwai Oh (오성회)
Email: songhwai (at) snu.ac.kr
Office Hours: Friday 2:00-3:00PM
Office: Building 133 Room 405
Course Number: 430.457
Time: TTh 5:00-6:15 PM
Location: Building 301 Room 201
TA: Kyunghoon Cho (조경훈)
Email: kyunghoon.cho (at) cpslab.snu.ac.kr
Office: Building 133 Room 610
TA: Hyemin Ahn (안혜민)
Email: hyemin.ahn (at) cpslab.snu.ac.kr
Office: Building 133 Room 610

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.

Project


Announcements


  • [10/02] The midterm will be held in class on 10/23 (Thur). The exam is closed-book but you can bring one sheet (A4) of hand written notes on a single side (the other side must be blank). You have to turn in this cheat sheet with your exam.
  • [09/04] There was a typo in lecture 2 notes. A random variable is a function from Omega (sample space) to a real number.
  • [07/29] Please read the Ethics of Learning.

Schedule


Week Reading Date Lecture Date Lecture
1 AIMA Ch. 13 9/2
  • Introduction
9/4
  • Review of probability
2 AIMA Ch. 14.1-14.3 9/9
  • Thanksgiving
9/11
  • Bayesian networks
3   9/16
  • No class
9/18
  • No class
4 AIMA Ch. 14.4-14.6,
   Ch. 15.1-15.2
9/23
  • Inference in Bayesian networks
9/25
  • Dynamic models
5 AIMA Ch. 15.3-15.6 9/30
  • Hidden Markov models
  • Kalman filtering
10/2
  • Kalman filtering
  • Dynamic Bayesian networks
6 AIMA Ch. 18.1-18.4 10/7
  • Supervised learning
  • Decision trees
10/9
  • Hangul Day (holiday)
7 AIMA Ch. 18.6-18.7 10/14
  • Linear regression
  • Linear classification
10/16
  • Artificial neural networks
8 AIMA Ch. 18.8 10/21
  • Nonparametric models
10/23
  • Midterm
9 AIMA Ch. 18.9,
   Ch. 20
10/28
  • Support vector machines
10/30
  • Bayesian learning
10   11/4
  • EM algorithm
11/6
  • Computer vision (intro)
11 AIMA Ch. 24 11/11
  • Computer vision
11/13
  • Computer vision
12 AIMA Ch. 16.1-16.7
   Ch. 17.1-17.4
11/18
  • Utility theory
  • Decision networks
11/20
  • Markov decision processes
13 AIMA Ch. 21 11/25
  • POMDPs
11/27
  • Reinforcement learning
  • Pedestrian detection
14 AIMA Ch. 25 12/2
  • Robotics
12/4
  • Localization and mapping
15   12/9
  • SLAM
12/11
  • Path planning

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
  • Computer Vision:
    • Image formation, Edge detection, Texture, Optical flow, Image segmentation
    • Object recognition, Reconstructing the 3D world
  • Robotics:
    • Localization and mapping, Motion planning, Planning uncertain movements, Moving
    • Robotic software architectures, Application domain