Course Information

Introduction to Intelligent Systems - Fall 2024

Instructor: Prof. Songhwai Oh (오성회)
Email: songhwai (at) snu.ac.kr
Office Hours: Friday 3:00-4:00PM
Office: Building 133 Room 403
Course Number: 430.457
Time: MW 11:00-12:15 PM
Location: Online (Building 301 Room 104)

TA-1: Yoseph Park (박요셉)
Email: yoseph.park (at) rllab.snu.ac.kr
Office: Building 301 Room 718

TA-3: Subin Shin (신수빈)
Email: subin.shin (at) rllab.snu.ac.kr
Office: Building 301 Room 718

TA-2: Minsoo Kim (김민수)
Email: minsoo.kim (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

Project and Announcements

Schedule

Week
Reading
Date
Lecture
Date
Lecture
1
 AIMA Ch. 1, Ch. 12
 9/2
  • Introduction
  • Traditional AI
9/4
  • Review of probability
2

AIMA Ch. 13.1 - 13.4

9/09
  • Bayesian networks
  • Exact inference in Bayesian networks
9/11
  • Exact inference in Bayesian networks
  • Approximate inference in Bayesian networks
  • (Makeup) Introduction to ROS
3
 
9/16
  • (Thanksgiving Holiday)
9/18
  • (Thanksgiving Holiday)
4

9/23
  • (No class)
9/25
  • (No class)
5

AIMA Ch. 14.1 - 14.3

9/30
  • Dynamic models
  • Inference in dynamic models
10/2
  • Hidden Markov models
6
AIMA Ch. 14.4-14.5, Ch. 19.1 - 19.2
10/7
  • Kalman filtering
  • Kalman filtering (vector case)
10/9
  • (Holiday)
  • Dynamic Bayesian networks
  • Supervised learning
7
AIMA Ch. 19.3 - 19.4, 19.6
10/14
  • (No class)
  • Decision trees
  • Generalization error
10/16
  • (No class)
  • Linear regression
8
 AIMA Ch. 19.6, Ch. 22.1
10/21
  • Linear classification
  • Artificial neural networks
10/23
  • Midterm
    - Time: 11:00 AM
    - Location: in class
9
AIMA Ch. 22, Ch. 19.7
10/28
  • Deep learning (intro)
  • CNN (Part 1, Part 2)
10/30
  • RNN
  • Nonparametric models
10
AIMA Ch. 21.1 - 21.3
11/4
  • Support vector machines
11/6
  • Bayesian learning
  • Learning with complete data
11
AIMA Ch. 15.1 - 15.4
11/11
  • EM algorithm
11/13
  • Utility theory
  • Decision networks
12
AIMA Ch. 15.5 - 15.6, Ch. 16
11/18
  • Markov decision processes
  • POMDPs
11/20
  • Reinforcement learning
  • Deep reinforcement learning
13
AIMA Ch. 23
11/25
  • Deep reinforcement learning
  • Soft and Sparse MDPs
11/27
  • Robotics (intro)
14
AIMA Ch. 26
12/2
  • Localization
  • Mapping
12/4
  • SLAM
  • Motion planning
15
AIMA Ch. 27
12/9
  • Computer vision
12/11
  • Computer vision: applications
 
 
 
 
12/13
  • RC Car Racing Challenge
    - Time: 12:30 PM
    - Location: Room 401, Building 300

Textbook

  • [Required] Stuart Russell and Peter Norvig. Artificial Intelligence: A Modern Approach (4th Edition, Global), Prentice Hall, 2020/2021. (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
    • Robotic software architectures, Application domains

  • Computer Vision:

    • Image formation, Edge detection, Texture, Optical flow, Image segmentation
    • Object recognition, Reconstructing the 3D world