CPSC 633-600 Machine Learning:
Spring 2013

Syllabus

NEWS: 4/26/13, 05:39PM (Fri)
  • [04/26/13] Upload your presentation files to elearing ASAP.
  • [04/26/13] Final project report due by 5/8 11:59pm. Upload to elearning. Degree candidates -- submit earlier (grades due 5/9).
  • [04/26/13] Exam #2 grades uploaded. Retake: 5/7 8am-9am.
  • [04/25/13] Project presentation and order:
    [4/29]: 1, 2, 16, 19, 12, 20, 14
    [4/30]: 7, 3, 6, 4, 11, 5, 10
    [5/07]: 22, 8, 9, 15, 21, 17, 13
  • [04/25/13] Homework 3 solution posted (requires password).
  • --------------------
  • [04/22/13] Project presentation poll
  • [04/19/13] Exam #2 poll
  • --------------------
  • [04/05/13] Jochen Fröhlich's Neural Net/SOM demo (click on "Sample Applet": requires JAVA)
  • [04/04/13] Homework #3 uploaded. Due 4/19, in class (or online by 10:20am).
  • --------------------
  • [03/27/13] Exam #1 retake will be tomorrow (Thu 3/28) at 6pm 5pm-6pm (session 1) and 6pm-7pm (session 2) in HRBB 302. Those who cannot make it, email the instructor. This is a closed book, closed note exam (no cheat sheets allowed).
  • --------------------
  • [03/26/13] Ken Stanley's web page (look for NEAT demos)
  • --------------------
  • [03/20/13] Homework 2 pt 2. Deadline extended to 11:59pm Friday (3/22).
  • --------------------
  • [03/08/13] Term Project details announced.
  • [03/08/13] Homework 2, part 2 announced. Due 3/22, 10:20am (hardcopy or elearning). NOTE: homework has been slightly updated.
  • --------------------
  • [03/05/13] Term project proposal will be due by 3/18 (Monday), in class. Form a team of up to 3 members.
  • --------------------
  • [03/01/13] Exam on Wednesday 3/6, in class. You may bring one sheet of hand-written notes (US letter, may use both sides; printed or photocopied notes will be confiscated).
  • --------------------
  • [02/25/13] Old exams uploaded. The exam next week will cover old-exam1.pdf and old-exam2.pdf. Solutions will not be provided.
  • --------------------
  • [02/23/13] Homework 2 announced: hw2.pdf. Due date 3/1 (Friday) In Class (10:20am) (submit on elearning by 10:20am or bring a hard copy to class).
  • --------------------
  • [02/15/13] Homework 1 deadline extended to 2/22 Friday 11:59pm.
  • [02/11/13] Homework 1 announced: hw1.pdf (topics: supervised learning [general], multilayer perceptrons). Due date: 2/25 2/18 (Monday) 11:59pm. Submit to elearning.tamu.edu.
  • [02/11/13] This week's schedule has been corrected (no class on Wednesday).
  • --------------------
  • [01/10/13] The class is currently full. Please file a force request if you want to be considered: https://csnet.cs.tamu.edu/apps/forces/ (Note: non-CS students: you do not need to login).
  • [01/10/13] Course web page goes online.
  • ---------------------------------------------------------
  • For older announcements, see the archive
Read-Only Bulletin Board.: 1/7/13, 03:21PM (Mon)

Page last modified: 4/23/13, 09:52PM Tuesday.

General Information Resources Reading List Weekly Schedule Lecture Notes

I. General Information

Instructor:

Dr. Yoonsuck Choe
Email: choe(a)tamu.edu
Office: HRBB 322B
Phone: 845-5466
Office hours: 9:00am-10:00am, Wed/Fri

TA:

Wen Li
Email: wen.li(a)neo.tamu.edu
Office: HRBB 311D
Phone: N/A
Office hours: Tue/Thu 4pm-5pm.

Prerequisite/Restrictions:

CPSC 420, 625, or consent of instructor.

Lectures:

MWF 10:20am–11:10am, ZACH 105B.

Introduction:

Machine learning is the study of self-modifying computer systems that can acquire new knowledge and improve their own performance; survey machine learning techniques, which include induction from examples, Bayesian learning, artificial neural networks, instance-based learning, genetic algorithms, reinforcement learning, unsupervised learning, and biologically motivated learning algorithms. Prerequisite: CPSC 420 or 625.

Goal:

The goal of this course is to

  1. learn various problems and solution strategies in machine learning.
  2. learn practical methodology for applying ML algorithms to problem domain of your choice.

Textbook:

Administrative details:

  1. Computer accounts: if you do not have a unix account, ask for one on the CS web page.
  2. Programming languages permitted: C/C++, Java, or Matlab (or octave), and must be executable on CS unix hosts or other public systems in the departmental lab.

Topics to be covered:

See the Weekly Schedule section for more details. The content will closely reflect a combination of Alpaydin + Mitchell.

Grading:

  1. 3 assignments (including written and programming components), 15% each = 45%
  2. 2 exams (in class), 15% each = 30%
  3. Term project 15%
  4. Class participation 10% (repeated absences in the class will weigh most heavily [in the negative direction] in the determination of this score)
The cutoff for an `A' will be at most 90% of total score, 80% for a `B', 70% for a `C', and 60% for a `D'. However, these cutoffs might be lowered at the end of the semester to accomodate the actual distribution of grades.

Academic Integrity Statement:

AGGIE HONOR CODE: An Aggie does not lie, cheat, or steal or tolerate those who do.

Upon accepting admission to Texas A&M University, a student immediately assumes a commitment to uphold the Honor Code, to accept responsibility for learning, and to follow the philosophy and rules of the Honor System. Students will be required to state their commitment on examinations, research papers, and other academic work. Ignorance of the rules does not exclude any member of the TAMU community from the requirements or the processes of the Honor System.

For additional information please visit: http://aggiehonor.tamu.edu/

Local Course Policy:

Students with Disabilities:

The Americans with Disabilities Act (ADA) is a federal anti-discrimination statute that provides comprehensive civil rights protection for persons with disabilities. Among other things, this legislation requires that all students with disabilities be guaranteed a learning environment that provides for reasonable accommodation of their disabilities. If you believe you have a disability requiring an accommodation, please contact the Department of Student Life, Services for Students with Disabilities, in Cain Hall or call 845-1637.

Resources:

  1. UCI Machine Learning Repository: datasets to test machine learning algorithms.
  2. Research resources page
  3. Ganeral reading list (u: p: ): includes short blurb about how to find, read, and critique others' work. This list is not the course reading list.

III. Weekly Schedule and Class Notes

Week
Date
Topic
Reading
Assignments
Notices and Dues
Notes
1 1/14 Introduction Alpaydin chap 1; Mitchell 1.1–1.2, 1.3–1.5     slide01.pdf
slide01b.pdf
1 1/16      
1 1/18      
2 1/21 Martin Luther King day No class    
2 1/23 Supervised Learning (general) Alpaydin chap 2; Mitchell 7.1–7.2, 7.4     slide02.pdf
2 1/25      
3 1/28      
3 1/30 Multilayer perceptrons Alpaydin chap 11; Mitchell chap 4     slide03.pdf
3 2/1      
4 2/4      
4 2/6      
4 2/8      
5 2/11   Homework 1 announced  
5 2/13 Online lecture (class will not meet) Watch Geoff Hinton's Google TechTalk on Deep Learning in Neural Networks    
5 2/15 Guest lecture Chul Sung (Ph.D. student) will talk about incremental learning based on PCA    
6 2/18 Decision tree learning Alpaydin chap 9; Mitchell chap 3   Homework 1 due slide04.pdf
6 2/20      
6 2/22   Homework 2 announced Homework 1 due
7 2/25 Reinforcement learning Alpaydin chap 18; Mitchell chap 13     slide05.pdf
7 2/27      
7 3/1     Homework 2 due
8 3/4 Reinforcement learning Advanced topics     slide05.pdf
8 3/6 Exam #1        
8 3/8 Term project ideas   Homework 2 announced  
9 3/11 Spring break No class      
9 3/13 Spring break No class      
9 3/15 Spring break No class      
10 3/18 Genetic Algorithms Mitchell chap 9   Term project proposal due (in class) slide06.pdf
10 3/20      
10 3/22   Homework 3 TBA Homework 2 due (in class)
11 3/25 Genetic Algorithms: Advanced topics slide07 will not be covered.     slide07.pdf
11 3/27 Dimensionality reduction Alpaydin chap 6: 6.1–3, 6.7, 6.8     slide08.pdf
11 3/29 No class Reading Day   Homework 3 Due
12 4/1      
12 4/3 Local models Alpaydin chap 12     slide09.pdf
12 4/5   Homework 3 Announced  
13 4/8 Bayesian learning Mitchell chap 6     slide10.pdf
13 4/10      
13 4/12      
14 4/15     Term project interim report due (in class) slide10.pdf
14 4/17      
14 4/19 Kernel machines Alpaydin 13.1–13.5   Homework 3 Due slide11.pdf
15 4/22      
15 4/24 Learning in biological vision Miikkulainen et al. (2005)     web_link;
15 4/26 Exam #2        
16 4/29 Project presentation      
164/30(Tue)Project presentation  Term project reports due: May 8 11:59am (degree candidates: please submit earlier) 


$Id: index.php,v 1.4.1.7 2003/11/13 00:02:12 choe Exp choe $