Introduction to Intelligent Systems (430.457) Spring 2015

Instructor: Prof. Songhwai Oh (오성회)
Email: songhwai (at) snu.ac.kr
Office Hours: Friday 3:00-4:00PM
Office: Building 133 Room 405
Course Number: 430.457
Time: MW 2:00-3:15 PM
Location: Building 301 Room 104
TA: Seunggyu Chang (장승규)
Email: seunggyu.chang (at) cpslab.snu.ac.kr
Office: Building 301 Room 718
TA: Kyoungjae Lee (이경재)
Email: kyoungjae.lee (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

Finale

 

Project

Announcements

  • [04/20] The midterm will cover up to lecture 11 (EM algorithm).
  • [04/06] The midterm will be held in class on 04/29 (Wed). 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.

Schedule

Week Reading Date Lecture Date Lecture
1 AIMA Ch. 13 3/2
  • Introduction
3/4
  • Review of probability
2 AIMA Ch. 14.1-14.6 3/9
  • More on probability
  • Bayesian networks
3/11
  • Inference in Bayesian networks
3 AIMA Ch. 15 3/16
  • Dynamic models
  • Inference in dynamic models
3/18
  • Hidden Markov models
4 AIMA Ch. 18.1-18.4 3/23
  • Kalman filtering
  • Dynamic Bayesian networks
3/25
  • Supervised learning
  • Decision trees
5 AIMA Ch. 18.6-18.7 3/30
  • Linear regression
  • Linear classification
4/1
  • Artificial neural networks
6 AIMA Ch. 18.8-18.9 4/6
  • Nonparametric models
4/8
  • Support vector machines
7 AIMA Ch. 20 4/13
  • Bayesian learning
4/15
  • EM algorithm
8 AIMA Ch. 16.1-16.7
    Ch. 17.1-17.4
4/20
  • Utility theory
  • Decision networks
4/22
  • Markov decision processes
9 AIMA Ch. 21 4/27
  • POMDPs
4/29
  • Midterm
10 AIMA Ch. 21,
    Ch. 25
5/4
  • Reinforcement learning
5/6
  • Robotics
11   5/11
  • Localization and mapping
5/13
  • SLAM
12 AIMA Ch. 24 5/18
  • Path planning
5/20
  • Computer vision (intro)
13   5/25
  • Holiday
5/27
  • No class
14 AIMA Ch. 24 6/1
  • Low-level vision
  • High-level vision
6/3
  • No class
15   6/8
  • No class
6/10
  • No class
16         Navigation Challenge (with Real Robots)
  • Date: 6/19 (Friday)
  • Time: 10:00AM-15:00PM
  • Room 610, Building 133

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