Course Information

Introduction to Intelligent Systems - Fall 2018
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 302 Room 519

TA-1: Jaegu Choy (최재구)
Email: jaegu.choy (at) cpslab.snu.ac.kr
Office: Building 301 Room 718
Office Hours: Friday 14:00~15:30

TA-2: Obin Kwon (권오빈)
Email: obin.kwon (at) rllab.snu.ac.kr
Office: Building 301 Room 718
Office Hours: Friday 14:00~15:30

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

KakaoTalk_20181217_110832855.jpg   

Project and Announcements

  • Project Information
  • [12/10] Final Project (due: 12/14, 23:59 KST)
  • [11/19] Project 4 (due: 11/30, 23:59 KST)
  • [11/05] Project 3 (due: 11/17, 23:59 KST)
  • [10/15] Lecture 5 is updated. There was a bug in the Viterbi algorithm (backtracking part) and it is fixed in the revised version. The bug is reported by Wooseok Oh.
  • [10/11] Project 2 (due: 10/20, 23:59 KST)
  • [10/10] The midterm will be held in class on 10/24 (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.
  • [10/01] Project 1 (due: 10/10, 23:59 KST)
  • [09/20] Preliminary Project 2 (due: 9/28, 23:59 KST)
  • [09/17] Team up for the projects! The number of team members should be exactly 3. Please e-mail TA (jaegu.choy@cpslab.snu.ac.kr) about your team until 10/1 (Monday) 17:00 KST . The e-mail must includes 1) your team name, 2) each team members' name and 3) student ID. If you don't send an email, you'll be in randomly constructed team.
  • [09/05] Preliminary Project 1 (due: 9/19, 23:59 KST)
  • [08/20] Please read the Ethics of Learning.

Schedule

Week Reading Date Lecture Date Lecture
1 AIMA Ch. 13 9/3
  • Introduction
9/5
  • Traditional AI
2 AIMA Ch. 14.1 - 14.3 9/10
  • Review of probability
9/12
  • Bayesian networks
        9/14
  • Makeup lecture
  • Time: 5-8 PM
  • Location: 301-203
3 AIMA Ch. 14.4 - 14.5 9/17
  • Inference in Bayesian networks
9/19
  • Inference in Bayesian networks
  • Dynamic models

4   9/24
  • Holiday
9/26
  • Holiday
5   10/1
  • No class
10/3
  • Holiday
6 AIMA Ch. 15.1 - 15.2 10/8
  • Dynamic models
  • Inference in dynamic models
10/10
  • Hidden Markov models
  • Kalman filtering
7 AIMA Ch. 15.3 - 15.7, Ch. 18.1 - 18.2 10/15
  • Dynamic Bayesian networks
  • Supervised learning
10/17
  • Supervised learning
  • Decision trees
8 AIMA Ch. 18.3-18.4, 18.6-18.7 10/22
  • Linear regression
  • Linear classification
10/24
  • Midterm
  • Time: 11:00AM
  • Location: Building 301, Room 104
9 AIMA Ch. 18.8 - 18.9 10/29
  • Artificial neural networks
  • Deep learning
10/31
  • Deep learning
10 AIMA Ch. 20.1 - 20.2, 20.3 - 20.4 11/5
  • Nonparametric models
  • Support vector machines
11/7
  • Bayesian learning
11 AIMA Ch. 16 11/12
  • EM algorithm
11/14
  • Utility Theory
  • Decision networks
12 AIMA Ch. 17.1 - 17.4, Ch. 21 11/19
  • Markov decision processes
  • POMDPs
11/21
  • Reinforcement learning
  • Deep reinforcement learning
13 AIMA Ch. 25 11/26
  • Deep reinforcement learning
  • Robotics (intro)
11/28
  • Localization and mapping
14   12/3
  • No class
12/5
  • No class
15 AIMA Ch. 24 12/10
  • SLAM
12/12
  • Path planning
16  AIMA Ch. 24  12/17
  • Makeup lecture
  • Computer vision (intro)
  • Low-level vision
  • High-level vision
 12/19
  • Makeup lecture
  • Computer vision (intro)
  • Low-level vision
  • High-level vision
        12/21

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