DSA 5970, Applied Machine Learning, Spring 2017, Syllabus

Syllabus
DSA 5970 — Applied Machine Learning — Spring 2017

Course Title:

Applied Machine Learning

Instructor:

Dean Hougen, Devon Energy Hall 242, 405-325-3150, hougen@ou.edu

Teaching Assistant:

None!

Class Hours:

N/A (Online)

Office Hours:

Dean Hougen:: TBD, Devon Energy Hall 242
TA:: None!

Required Text Books:

Each student is required to have his or her own copy of the following textbooks.

Currently Under Consideration:

Machine Learning: a Probabilistic Perspective, Kevin Patrick Murphy, 2012, MIT Press
Learning From Data, Yaser S. Abu-Mostafa, Malik Magdon-Ismail, and Hsuan-Tien Lin, 2012, AMLBook
Data Mining: Practical Machine Learning Tools and Techniques, Ian H. Witten, Eibe Frank, and Mark A. Hall, 2011, Morgan-Kaufmann
Bayesian Reasoning and Machine Learning, David Barber, 2012, Cambridge University Press
Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies, John D. Kelleher, Brian Mac Namee, and Aoife D'Arcy, 2015, MIT Press
Machine Learning: A Bayesian and Optimization Perspective, Sergios Theodoridis, 2015, Academic Press
Machine Learning: The Art and Science of Algorithms that Make Sense of Data, Peter Flach, 2012, Cambridge University Press
An Introduction to Machine Learning, Miroslav Kubat, 2015, Springer

Students should read ahead the chapters and other materials that are expected to be covered in the class period (see the class schedule). Students should always bring their textbooks with them to class, including lectures/discussions, group work days, and exams.

Communication:

The primary means of transmitting class information to the students will be through announcements and discussions within Janux and via these web pages. You are responsible for announcements made through either or both of these means.

Occasionally, urgent information may be sent via email. You must ensure that the email address the University has on file for you is valid and is monitored by you. A test of the email addresses provided by the University will be made during the second week of class. You are responsible for notifying the instructor if you do not receive this test email.

Students may communicate with one another using the discussion forums in Janux or by other means outside of class as mutually agreed to by the students involved.

Expectations and Goals:

The prerequisites for this course are DSA 5005 Computing Structures (or CS 2413 Data Structures and CS 2813 Discrete Structures or Math 2513 Discrete Mathematics) and Math 3333 Linear Algebra or instructor permission. You are expected to have a sufficient background in Computer Science and Mathematics to be able to support projects involving machine learning. You are expected to have a working knowledge of a high-level object-oriented or imperative language, including a familiarity with its basic data types and control structures. A background in AI such as that provided by CS 4013/5013 Artificial Intelligence may be useful but is not a requirement.

By the end of this course, you should have a broad understanding of the field of machine learning and the most important algorithms therein, and be able to analyze machine-learning problems and their data, determine appropriate algorithmic approaches, refine data sets, apply machine learning algorithms and intelligently interpret and discuss their results.

Topics:

experimental design, prediction vs explanation, methodology of machine learning
data pre-processing, cleansing, normalization, and transformation; missing data
data representation, dimensionality reduction, feature selection, and feature extraction
pattern recognition, classification, clustering, regression model quality, error analysis, error metrics, performance prediction, cross-validation
decision trees, random forests, rule-based classification, boosting
artificial neural networks, deep learning, self-organizing maps
hidden Markov models, graphical models
support vector machines, kernel methods
evolutionary computation, reinforcement learning

Requirements:

The graded assignments and their contribution to a student's grade are given in the table below. (Subject to change.)

Assignment Type (number)	Percent of Grade
Homeworks (12) Projects (6) Exams (3)	10% (1% each, drop two lowest) 50% (10% each, drop lowest) 40% (10% first and second, 20% final)

All assignments in this course are to be done ALONE; the work submitted by a student MUST be the student's own.

You are responsible for the material covered during the recorded lecture sessions, whether or not it is also found in your textbooks or other assigned reading materials. Similarly, you are responsible for the material found in your textbooks and other assigned reading materials, whether or not it is also covered during the lecture sessions. In other words, you are responsible for the UNION of these sources of knowledge, as depicted by the entire shaded region of the Venn diagram below, not merely their intersection.

You may write your programs from scratch or may start from programs for which the source code is freely available on the web or through other sources (such as friends or student organizations). If you do not start from scratch, you must give a complete and accurate accounting of where all of your code came from and indicate which parts are original, which are changed, and which you got from which other source. Failure to give credit where credit is due is academic fraud and will be dealt with accordingly.

All work must properly cite sources. For example, if you quote a source in one of your technical paper reviews, you must include the quotation in quotation marks and clearly indicate the source of the quotation.

Late assignments will be penalized 20% per day late. (All parts of days will be rounded up.) After five days, you will not be able to turn in that assignment for credit. If you are worried about turning in the assignment late and losing points, turn in the assignment ahead of time. You will be turning in electronic copies of all projects and homeworks.

Copying another's work, or possession of electronic computing or communication devices in the testing area, is cheating and grounds for penalties in accordance with school policies.

Please see OU’s academic integrity website.

Accommodations:

Any student with a disability should contact the instructor so that reasonable accommodations may be made for that student.

Adjustments for Pregnancy/Childbirth Related Issues:

Should you need modifications or adjustments to your course requirements because of documented pregnancy-related or childbirth-related issues, please contact me as soon as possible to discuss. Generally, modifications will be made where medically necessary and similar in scope to accommodations based on temporary disability. Please see http://www.ou.edu/eoo/faqs/pregnancy-faqs.html for commonly asked questions.

Title IX Resources

For any concerns regarding gender-based discrimination, sexual harassment, sexual misconduct, stalking, or intimate partner violence, the University offers a variety of resources, including advocates on-call 24.7, counseling services, mutual no contact orders, scheduling adjustments and disciplinary sanctions against the perpetrator. Please contact the Sexual Misconduct Office 405-325-2215 (8-5) or the Sexual Assault Response Team 405- 615-0013 (24.7) to learn more or to report an incident.

Drop Policy:

Any student who fails to attend the first week of class may be dropped from the class.

Holidays:

It is the policy of the University to excuse the absences of students that result from religious observances and to provide without penalty for the rescheduling of examinations and additional required class work that may fall on religious holidays.

Related Documents:

Students should also read the related documents on Replacement Assignments or Extensions and Discussions of Scores and Grades.