Course Information

Introduction to Intelligent Systems - Fall 2019
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: Gunmin Lee (이건민)
Email: gunmin.lee (at) rllab.snu.ac.kr
Office: Building 301 Room 718

TA-3: Minjae Kang (강민재)
Email: minjae.kang (at) rllab.snu.ac.kr
Office: Building 301 Room 718

TA-2: Mineui Hong (홍민의)
Email: mineui.hong (at) rllab.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, neural networks, deep learning, 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

temp_1575598587114.-2121448555.jpeg

Project and Announcements

  • Project Information
  • [12/09] Final Project (due: 12/13, 23:59 KST)
  • [11/25] Project 4 (due: 12/06, 23:59 KST)
  • [11/13] Project 3 (due: 11/25, 23:59 KST)
  • [10/30] Project 2 (due: 11/13, 23:59 KST)
  • [10/14] Project 1 (due: 10/28, 23:59 KST)
  • [10/14] The midterm will be held in class on 10/23 (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.
  • [09/16] Preliminary Project 2 (due: 9/25, 23:59 KST)
  • [09/02] Preliminary Project 1 (due: 9/16, 23:59 KST)
  • [08/26] Please read the Ethics of Learning.

Schedule

Week Reading Date Lecture Date Lecture
1 AIMA Ch. 13 9/2
  • Introduction
9/4
  • Traditional AI
  • Review of probability
        9/6
  • Makeup lecture
  • Time: 5-8 PM
  • Location: 301-104
2 AIMA Ch. 14.1 - 14.3 9/9
  • Bayesian networks
9/11
  • Inference in Bayesian networks
3 AIMA Ch. 14.4 - 14.5 9/16
  • Inference in Bayesian networks
  • Dynamic models

9/18
  • Inference in dynamic models
4 AIMA Ch. 15.1 - 15.7 9/23
  • Hidden Markov models
  • Kalman filtering
9/25
  • Dynamic Bayesian networks
5 AIMA Ch. 18.1 - 18.3 9/30
  • Supervised learning
  • Decision trees
10/2
  • Linear regression
6 AIMA Ch. 18.4, 18.6 10/7
  • Linear classification
  • Artificial neural networks
10/9
  • Holiday
7 AIMA Ch. 18.7 10/14
  • Deep learning
    • Introduction
    • CNN (Part 1, Part 2)
    • RNN
10/16
  • Deep learning
8 AIMA Ch. 18.8 - 18.9 10/21
  • Nonparametric models
  • Support vector machines
10/23
  • Midterm
    • in class
9 AIMA Ch. 20.1 - 20.2 10/28
  • Bayesian learning
10/30
  • No class
10   11/4
  • No class
11/6
  • No class
11 AIMA Ch. 20.3, Ch. 16 11/11
  • EM Algorithm
11/13
  • Utility Theory
  • Decision networks
12 AIMA Ch. 17.1 - 17.4, Ch. 21 11/18
  • Markov decision processes
  • POMDPs
11/20
  • Reinforcement learning
  • Deep reinforcement learning
13 AIMA Ch. 25 11/25
  • Robotics (intro)
11/27
  • Localization and mapping
14   12/2
  • SLAM
12/4
  • Path planning
15 AIMA Ch. 24 12/9
  • Computer vision
12/11
  • Computer vision
        12/20

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
    • Deep learning
    • 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