CSCE 633: Machine Learning (Spring
2018)
Instructor
Dr. Zhangyang (Atlas) Wang
Email: atlaswang@tamu.edu
Office: 328C HRBB (visit by appointment only
except office hours)
Webpage: http://www.atlaswang.com
TA: Ye
Yuan
Email: ye.yuan@tamu.edu
Office: 320 HRBB
Time and Location
·
Lecture time: 12:45 - 2:00
pm, every Tuesday and Thursday
·
Lecture location: CHEN
104
·
Instructor Office Hour: 2:00
– 3:00 pm every Thursday
·
TA Office Hour: 2:00 – 3:00
pm every Wednesday
·
Class fully seated. NO AUDITION ALLOWED.
Course Description
Machine learning is a sub-field of Artificial Intelligence that gives
computers the ability to learn and/or act without being explicitly programmed.
Topics include various supervised, unsupervised and reinforcement learning approaches
(including deep learning), optimization procedures, and statistical inference.
Course Goal
The students will digest and practice their knowledge and skills by class
discussion and course presentation, and obtain in-depth experience with a
particular topic through a final project.
Evaluation Metrics
Grading will be based on three in-class quizzes (10% each), one mid-term exam (20%),
and one final project (50%)
(proposal 10% + presentation 15% + code review 10% + report 15%).
There will be no final exam.
Final project Collaborations and teamwork are encouraged, but must be coordinated and
approved by the instructor. A team can only have 2 members. Extra credits
(>50%) will be given to:
- One project to receive the Best
Project Award, voted by all class members. (+5%)
- Projects of interdisciplinary topics and novel application domains. (+2%)
The project proposal, report and codes should be all submitted via
email. For late submission, each additional late day will incur a 10% penalty.
The grading policy is as follows:
90-100: |
A
|
80-89: |
B
|
70-79: |
C
|
60-69: |
D
|
<60: |
F |
Project
It's important that you work on a real machine learning project, or a
real problem in some relevant domain, so that you earn first-hand experience how
the computational models are bridged with the high complexity and uncertainty
of the real world.
You're encouraged to develop your project ideas, or you can follow the
suggested topic (details will be given in course slides). The instructor is
available to discuss and shape the project. The scale of the project should be scheduled
as one semester long.
By the end of the semester, you should submit your code and data for
this project, write a project report of maximum 8 pages (plus additional pages
containing only references) using the standard CVPR paper template, and
prepare a class presentation. The instructor will be happy to help develop promising
project ideas into a formal publication during or after the semester, if you
wish so.
Prerequisite
· Students should have taken the following courses or equivalent: Data
Structure and Algorithms (CSCE 221), Linear Algebra (MATH 304 or MATH
323), Numerical Methods (MATH 417).
·
Coding experiences with
Matlab, C/C++ or Python are assumed.
· Previous knowledge of machine learning, computer vision signal
processing or data mining will be helpful, but not necessary.
Reading Materials
This
course does not follow any textbook closely. Among many recommended readings
are:
1. Introduction to Machine Learning, Ethem Alpaydin (2014), MIT Press. [Book home page (3rd edition)] [Book home page (2nd edition)] [Book home page (1st edition)]
2. Pattern
Recognition and Machine Learning, Christopher
M. Bishop (2006). [A Bayesian view]
3. The Elements of Statistical Learning, Jerome H. Friedman, Robert Tibshirani, and Trevor Hastie (2001),
Springer. [Warning: not so elementary but quite insightful]
4. Sparse Coding and its Applications in Computer Vision, Wang et. al. (2015), WorldScientific.
5. Convex Optimization, Stephen Boyd and Lieven
Vandenberghe (2004), Cambridge University
Press. [Their CVX
toolbox is a great Matlab-based
convex optimization tool for beginners]
6. Distributed
optimization and statistical learning via the alternating direction method of
multipliers, Stephen Boyd et. al. (2011).
[Dedicated reference for ADMM]
7. Linear Algebra and its Applications, Gilbert Strang (1988). [For those
who want to simply keep a concise reference for linear algebra, my best
recommendation is The Matrix Cookbook]
8. Deep Learning, Ian Goodfellow, Yoshua
Bengio and Aaron Courville (2016), MIT Press.
Lecture Notes (in PDF format) will be uploaded to the course webpage no
more than 24 hours AFTER each class.
Attendance and Make-up Policies
Every student should attend the
class, unless you have an accepted excuse. Please check student rule 7 http://student-rules.tamu.edu/rule07 for details.
Academic Integrity
Aggie Code of Honor: An Aggie
does not lie, cheat or steal, or tolerate those who do. see: Honor
Council Rules and Procedures
Americans with Disabilities Act
(ADA) Statement
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 Disability
Services, currently located in the Disability Services building at the Student
Services at White Creek complex on west campus or call 979-845-1637. For
additional information, visit http://disability.tamu.edu.
Week 1 |
|
01/16 |
Introduction [Link] |
01/18 |
Linear Algebra and Matrix Analysis [Link] |
Week 2 |
|
01/23 |
No Class
(scheduled travel) |
01/25 |
Vector Space and Optimization [Link] |
Week 3 |
|
01/30 |
Statistical Learning Theory [Link] |
02/01 |
Dimensionality
Reduction and Regression [Link] |
Week 4 |
|
02/06 |
No Class (scheduled travel) |
02/08 |
Classification and Clustering [Link] |
Week 5 |
|
02/13 |
Support
Vector Machine and Kernel Machine (i) [Link] |
02/15 |
No Class
(scheduled travel) |
Week 6 |
|
02/20 |
Support
Vector Machine and Kernel Machine (ii) [Link] |
02/22 |
Sparse
Learning (i) [Link] |
Week 7 |
(Due by Week 7 Sunday: Submitting Project
Proposal) |
02/27 |
Midterm Exam |
03/01 |
Sparse Learning (ii) [Link] |
Week 8 |
|
03/06 |
Low-Dimensionality in High-Dimensional Spaces [Link] |
03/08 |
Multi-Task Learning and Transfer Learning [Link] |
Week 9 |
|
03/13 |
No Class (Spring Break) |
03/15 |
No Class (Spring Break) |
Week 10 |
|
03/20 |
Decision Tree, Random Forests and Ensemble [Link] |
03/22 |
Deep
Learning (i): History and Basics [Link] |
Week 11 |
|
03/27 |
Deep Learning (ii): Regularization Techniques [Link] |
03/29 |
Deep Learning (iii): Application Tour in Image Processing |
Week 12 |
|
04/03 |
Deep Learning (iv): Implementation Issues [Link] |
04/05 |
No Class
(scheduled travel) |
Week 13 |
|
04/10 |
Deep Learning (v): New Trends and Tricks [Link] |
04/12 |
Deep
Learning (vi): Deep Reinforcement
Learning [Link] |
Week 14 |
|
04/17 |
Final Project Presentations (i) [Free Project] |
04/19 |
Final Project Presentations (ii) [Free Project] |
Week 15 |
|
04/24 |
No Class
(scheduled travel) |
04/26 |
Final Project Presentations (iii) [Free Project] |
Week 16 |
|
05/01 |
Final Project Presentations (iv) [Challenge] |