Introduction to Machine Learning
  • 2015 Fall Undergraduate Course in Computer Science and Engineering
  • Instructor: Prof. Byoung-Tak Zhang
  • TA: Cheolho Han (Room: 302-314-1, Tel.: 880-1847)
  • Classroom: 302-107
  • Time: Tue & Thu, 11:00-12:15
  • Reference:
    • [1] Bishop, C. M., Pattern Recognition and Machine Learning, Springer-Verlag, 2006.
  • Evaluation:
    • Two open-book exams (50%)
    • Two miniprojects + two reports + one poster presentation (40%)
    • Participation and discussion (10%)
  • Announcement:
    • Classes on Sep. 8 and 10 were cancelled.
    • A make-up class will be on Sep. 7, at 7pm.
    • The classroom has moved from Rm. 209 to Rm. 107.
    • Project 1 came out. You can do it by MATLAB or Python;
      RBFN  mini-project 1_MATLAB  MNIST_Dataset.mat  mini-project 1_Python 
    • Classes on Sep. 17 and Oct. 1 were cancelled.
    • No class on Sep. 29 (Chuseok holidays).
    • A make-up class will be on Sep. 22, at 7pm.
    • If you have any questions about the course, feel free to visit the following board board.
    • You can submit your work on Project 1 by 11:59:59pm on Oct. 15 with no penalty.
    • Regular classes on Oct. 8 and 13 will be substituted with recitations in Rm. 311-1 (Software Lab.).
    • The midterm exam will be on Oct. 27.
    • No class on Oct. 29.
    • Regular classes on Nov. 3 and 5 will be substituted with recitations in Rm. 311-1 (Software Lab.).
    • Classses on Nov. 17 and 19 were cancelled. will be substituted with recitations in Rm. 311-1 (Software Lab.).
    • A make-up class will be on Nov. 9, at 7pm.
    • Please visit the following page:  project error messages
      With the penalty, you are allowed to correct the errors and submit the source codes again
      till 11:59:59pm on Nov. 4.
    • Poster Presentation Announcement
      poster
    • Project 2 came out. You can do it by MATLAB or Python;
      project 2
    • The final exam is on Dec. 10, 11am - 12:30pm
  • Course Description:
    • Machine learning studies learning systems, i.e. agents that improve their performance automatically by acquiring knowledge through experience and data collected from interaction with their environments. Machine learning plays a key role in modern artificial intelligence and is applied to a wide range of practical applications, including data mining, information retrieval, natural language processing, computer vision, robotics, social networks, and mobile services. The objective of this course is two-fold. One is to provide the students with the principles and mathematical tools for machine learning. Another is to introduce the architectures and algorithms for representative models of machine learning. These include pattern classification models, kernel machines, clustering algorithms, and probabilistic graphical models.
    • Lecture Schedule
    • Week Topics Slides

      Week 1

      (9/1, 9/3)
      • What's Machine Learning and Why?
      • Classification theory
      		 Intro. to ML
      Lec. 1 ML Overview
      Pictures of Blackboard (9/3)
      01  02
      		  

      Week 2

      (9/8, 9/10)
      • Classification 1
      • Classification 2
      		 Pictures of Blackboard (9/7)
      03  04  05  06  07  08  09 

      Week 3

      (9/15, 9/17)
      • Classification 3
      • Classification 4
      		 Pictures of Blackboard (9/15)
      10  11 

      Week 4

      (9/22, 9/24)
      • Bayesian inference and information theory
      • Kernel machine 1
      		 Pictures of Blackboard (9/22)
      12  13  14  15  16  17
      Pictures of Blackboard (9/24)
      18  19 

      Week 5

      (10/1)
      • Kernel machine 2
      		  

      Week 6

      (10/6, 10/8)
      • Kernel machine 3
      • Kernel machine 4
      • Due of project 1 report (10/8)
      		 Pictures of Blackboard (10/6)
      20  21
      Recitation (10/8)
      MATLAB_Tutorial1  Problem 

      Week 7

      (10/13, 10/15)
      • Clustering 1
      • Clustering 2
      		 Recitation (10/13)
      MATLAB_Tutorial2  Problem 

      Week 8

      (10/20, 10/22)
      • Clustering 3
      • Clustering 4
      		 Pictures of Blackboard (10/20)
      22  23
      Pictures of Blackboard (10/22)
      24  25

      Week 9

      (10/27, 10/29)
      • Exam 1
      • Graphical models 1
      		  

      Week 10

      (11/3, 11/5)
      • Graphical models 2
      • Graphical models 3
      		 Recitation (11/3)
      Problem
      Recitation (11/5)
      Problem

      Week 11

      (11/10, 11/12)
      • Graphical models 4
      • Preliminary posters (projects 1 + 2)
      		 Pictures of Blackboard (11/9)
      26  27  28
      Pictures of Blackboard (11/12)
      29

      Week 12

      (11/17, 11/19)
      • Poster presentation (projects 1 + 2)
      • Deep learning 1
      		 Recitation (11/17)
      Problem
      Recitation (11/19)
      Problem

      Week 13

      (11/24, 11/26)
      • Deep learning 2
      • Deep learning 3
      		 Pictures of Blackboard (11/23)
      30  31  32  33

      Week 14

      (12/1)
      • Review and Discussion
      		 Lecture Notes (12/1)
      DL  DHN  NGML

      Week 15

      (12/10)
      • Exam 2
      		  

      Week 16

      (12/14)
      • Due of project 2 report (12/14)
      		  
    This page is maintained by Cheolho Han
    Last update: 2015. 12. 01.