|
|
|
General Information | Resources | Reading List | Weekly Schedule | Lecture Notes |
I. General Information |
Dr. Yoonsuck Choe
Email: choe(a)tamu.edu
Office: HRBB 322B
Phone: 845-5466
Office hours: 3pm-4pm, MWF
CPSC 420, 625, or consent of instructor.
MWF 10:20am–11:10am HRBB 104.
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.
The goal of this course is to
See the Weekly Schedule section for more details. The content will closely reflect Mitchell (1997).
Grading will be on the absolute scale. 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.
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://www.tamu.edu/aggiehonor/
Local Course Policy:
- All work should be done individually and on your own unless otherwise allowed by the instructor.
- Discussion is only allowed immediately before, during, or immediately after the class, or during the instructor's office hours.
- If you find solutions to homeworks or programming assignments on the web (or in a book, etc.), you may (or may not) use it. Please check with the instructor.
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.
III. Weekly Schedule and Class Notes |
|
|
|||||
1 | 1/15 | MLK Day (Holiday) | ||||
1 | 1/17 | No class | Morning classes canceled due to the weather | |||
1 | 1/19 | Introduction | 1.1–1.2, 1.3–1.5 | slide01.pdf |
||
2 | 1/22 | Concept learning | 2.1–2.4 | slide02.pdf |
||
2 | 1/24 | Concept learning | 2.5–2.6 | slide02.pdf |
||
2 | 1/26 | Concept learning | 2.7–2.8 | slide02.pdf |
||
3 | 1/29 | ANN | 4.1–4.4 | slide03.pdf |
||
3 | 1/31 | ANN | 4.5–4.6 | slide03.pdf |
||
3 | 2/2 | ANN | 4.7–4.9 | Homework 1 [hw1.pdf] | slide03.pdf |
|
4 | 2/5 | ANN (applications) | TBA | slide03.pdf |
||
4 | 2/7 | Decision tree | 3.1–3.4 | slide04.pdf |
||
4 | 2/9 | Decision tree | 3.5–3.8 | Homework 1 Due, in class | slide04.pdf |
|
5 | 2/12 | Reinforcement learning | 13.1–13.3.3 | slide05.pdf |
||
5 | 2/14 | Quiz 1 | ||||
5 | 2/16 | Reinforcement learning | 13.3.4–13.5 | slide05.pdf |
||
6 | 2/19 | Reinforcement learning | 13.6–13.8 | Homework 2 [hw2.pdf] | slide05.pdf |
|
6 | 2/21 | Reinforcement learning (autonomous semantics) | slide06.pdf |
|||
6 | 2/23 | Reinforcement learning (autonomous semantics) | slide06.pdf |
|||
7 | 2/26 | Genetic algorithms | 9.1–9.3 | slide07.pdf |
||
7 | 2/28 | Genetic algorithms | 9.4–9.8 | slide07.pdf |
||
7 | 3/2 | Genetic algorithms (neuroevolution) | TBA | Homework 2 due for 5 point extra credit | slide08.pdf |
|
8 | 3/5 | Evaluating hypotheses | 5.1–5.3 | Homework 2 due, in class | slide09.pdf |
|
8 | 3/7 | Quiz 2 | ||||
8 | 3/9 | Evaluating hypotheses | 5.4–5.7 | slide09.pdf |
||
9 | 3/12 | Spring break | ||||
9 | 3/14 | Spring break | ||||
9 | 3/16 | Spring break | ||||
10 | 3/19 | Bayesian learning | 6.1–6.4 | slide10.pdf |
||
10 | 3/21 | Bayesian learning | 6.5–6.9 | slide10.pdf |
||
10 | 3/23 | Bayesian learning | 6.11–6.13 | slide10.pdf |
||
11 | 3/26 | Bayesian learning | 6.11–6.13 | slide10.pdf |
||
11 | 3/28 | Bayesian learning | 6.11–6.13 | slide10.pdf |
||
11 | 3/30 | Bayesian learning | 6.11–6.13 | slide10.pdf |
||
12 | 4/2 | Computational learning theory | 7.1–7.3 | slide11.pdf |
||
12 | 4/4 | Computational learning theory | 7.4–7.6 | slide11.pdf |
||
12 | 4/6 | No class | Reading day | |||
13 | 4/9 | Instance-based learning | 8.1–8.3; 8.4–8.7 | Homework 3 due, in class | slide12.pdf |
|
13 | 4/11 | Quiz 3 | ||||
13 | 4/13 | No class | Trip | |||
14 | 4/16 | Imitation learning | Rao et al. (2004) [PDF] | slide13.pdf |
||
14 | 4/18 | Learning in biological vision | Miikkulainen et al. (2005) | slide14.pdf |
||
14 | 4/20 | Learning in biological vision | Miikkulainen et al. (2005) | slide14.pdf |
||
15 | 4/23 | Committee machines (ensemble averaging and boosting) | Haykin (1999), Chapter 7 | slide15.pdf |
||
15 | 4/25 | Unsupervised learning | slide16.pdf |
|||
15 | 4/27 | No class | Trip | |||
16 | 4/30 | Project presentation | Amanda; Daniel & Xioa-lin; David; John & Belita | |||
16 | 5/1 | Project presentation | Andrew & Yuan-Teng; Hassan; Aditya and Vijay; Yoon & Han |