Course Information

Introduction to Intelligent Systems - Fall 2021
Instructor: Prof. Songhwai Oh (오성회)
Email: songhwai (at) snu.ac.kr
Office Hours: Friday 2:00-4:00PM
Office: Building 133 Room 605
Course Number: 430.457
Time: MW 11:00-12:15 PM
Location: Online (Building 301 Room 302)

TA-1: Jeongwoo Oh (오정우)
Email: jeongwoo.oh (at) rllab.snu.ac.kr
Office: Building 301 Room 718

TA-3: Jaeseok Heo (허재석)
Email: jaeseok.heo (at) rllab.snu.ac.kr
Office: Building 301 Room 718

TA-2: Jaeyeon Jeong (정재연)
Email: jaeyeon.jeong (at) rllab.snu.ac.kr
Office: Building 301 Room 718

TA-4: Minyoung Hwang (황민영)
Email: minyoung.hwang (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, nonparametric models, and reinforcement learning. 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 Challenge

rc_car.jpg

Project and Announcements

Schedule

Week Reading Date Lecture Date Lecture
1   9/1
  • Introduction
 

 

2

AIMA Ch. 13, Ch. 14.1 - 14.3

9/6
  • Traditional AI
  • Review of probability
  • ROS tutorial
9/8
  • Bayesian networks
3

AIMA Ch. 14.4 - 14.5

9/13
  • Exact inference in Bayesian networks
9/15
  • Approximate inference in Bayesian networks
4 AIMA Ch. 15.1 - 15.3 9/20
  • Holiday
9/22
  • Holiday
         

Makeup lecture

  • Dynamic models
  • Inference in dynamic models
5 AIMA Ch. 15.3 - 15.6 9/27
  • Hidden Markov models
9/29
  • Kalman filtering
  • Kalman filtering (vector case)
6 AIMA Ch. 18.1 - 18.4 10/4
  • Holiday
10/6
  • Dynamic Bayesian networks
  • Supervised learning
         

Makeup lecture

  • Decision trees
  • Generalization error
7 AIMA Ch. 18.6 - 18.7 10/11
  • Holiday
10/13
  • Linear regression
         

Makeup lecture

  • Linear classification
  • Artificial neural networks
8   10/18
  • Deep learning (intro)
  • CNN (Part 1, Part 2)
  • RNN
10/20

Midterm

  • Time: 11:00 - 1:00PM
  • Location: 301-302
9 AIMA Ch. 18.8 - 18.9 10/25
  • Nonparametric models
10/27
  • Support vector machines
10 AIMA Ch. 20.1 - 20.3 11/1
  • Bayesian learning
  • Learning with complete data
11/3
  • EM Algorithm
11 AIMA Ch. 16 11/8
  • Utility theory
11/10
  • Decision networks
12 AIMA Ch. 17.1 - 17.4, Ch. 21 11/15
  • Markov decision processes
  • POMDPs
11/17
  • Reinforcement learning
13 AIMA Ch. 25 11/22
  • Deep reinforcement learning
11/24
  • Robotics (intro)
14 AIMA Ch. 25 11/29
  • Localization
  • Mapping
12/1
  • SLAM
15 AIMA Ch. 24 12/6
  • Path planning
12/8
  • Computer vision: applications
  • Computer vision
         12/17  RC Car Racing Challenge

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