CSE 5523: Machine Learning

Course learning outcomes: Upon successful completion of this course, each student will be able to:

1. Understand basic concepts of machine learning and statistical pattern recognition
2. Implement basic machine learning and pattern recognition algorithms
3. Know how to compare, interpret and analyze results from the machine learning and pattern recognition methods
4. Apply classical machine learning and pattern recognition techniques for data analysis
5. Have basic ideas on how to develop proper machine learning and pattern recognition methods for different problems
6. Be able to implement a data analysis pipeline for a real-life problems using the concepts and techniques learned from this course

Instructor: William Schuler

• Office: Oxley 210
• Email: (my last name)@ling.osu.edu
• Office hours: Tuesday 11:00--12pm, Wednesday 4:00--5:00pm (link is on syllabus tab in Carmen), or by appointment (just email me)

TA: Mike Menart

• Email: (last name).2@buckeyemail.osu.edu

Meeting time and location: Tuesday and Thursday 9:35am-10:55am in Caldwell Lab 120.

Web site: http://www.ling.osu.edu/~schuler/courses/5523. The updated syllabus, assignments, slides, etc. will be posted here, so check it regularly.

Textbook: (optional) Kevin Murphy Machine Learning: a Probabilistic Perspective ISBN: 9780262018029

Course Content:

Wk	Due Monday 11:59PM	Lecture: Tuesday	Due Wednesday 11:59PM	Lecture: Thursday
1		8/24 python, pandas tutorials overview, background	Murphy ch 2.1-2.5	8/26 probability, distribution functions
2		(no class)	Murphy ch 3	9/2 --- PS1 handout generative models
3	Murphy ch 5.1-5.4	9/7 Bayesian statistics	Murphy ch 5.7, ch 6-6.2.1	9/9 decision theory, significance, permutation testing
4	9/13 PS1 due, Murphy ch 2.8	9/14 --- PS2 handout investor-train.csv investor-test.csv information theory	Murphy ch 16.1-16.4	9/16 decision trees
5		9/21 linear algebra notation	Murphy ch 4.1	9/23 continuous variables (Gaussians)
6	9/27 PS2 due Murphy ch 7.1-7.5	9/28 --- PS3 handout, sweet-train.csv, sweet-test.csv linear regression		9/30 (cont'd)
7	Murphy ch 12.2	10/5 dimensionality reduction, principal components	Murphy ch 8.1-8.3	10/7 logistic regression
8	10/11 PS3 due, Murphy ch 8.5	10/12 --- PS4 handout, iris-train.csv, iris-test.csv stochastic optimization, adam		(autumn break)
9	Murphy ch 16.5	10/19 multi-layer neural networks		10/21 convolutional neural nets
10	10/25 PS4 duei	10/26 --- PS5 handout, mileage-train.csv, mileage-test.csv RNNs, LSTMs		10/28 transformers, automatic differentiation
11	Murphy ch 14.1-14.2,14.4-14.5	11/2 support vector machines	Murphy ch 10-10.5	11/4 Bayes nets, HMMs, message-passing, inference
12	11/8 PS5 due, Murphy ch 19.1-19.3,19.5-19.6	11/9 --- PS6 handout, games.csv random fields		(Veterans Day)
13	Murphy ch 11.1-11.4	11/16 expectation maximization	Murphy ch 24.1-24.3	11/18 Dirichlet models, Gibbs sampling
14	11/22 PS6 due, Murphy ch 25.1-25.2	11/23 Dirichlet process models		(Thanksgiving Day)
15		11/30 project presentations		12/2 project presentations
16		12/7 project presentations		(end of term)
17	12/13 project due	(end of term)		(end of term)

Credit hours and work expectations: This is a 3-credit-hour course. According to Ohio State policy, students should expect around 3 hours per week of time spent on direct instruction (instructor content and Carmen activities, for example) in addition to 6 hours of homework (reading and assignment preparation, for example) to receive a grade of (C) average.

Course requirements:

• Regular attendance and active participation (10% of grade): this will include a project presentation. Presentations will be ordered alphabetically by last name (unless some reordering is necessary due to technical problems). Presentations should describe the task and techniques used and any results that are available. Presentations should each be about 5 minutes long through zoom (which will require a working microphone), and may or may not use slides at the presenter’s discretion. Group members may jointly present or may choose a single presenter to present during one of the members’ slots.
• Completing six problem set assignments (60% of grade), some paper and pencil, some programming and some preliminary project work (handed out about a week and a half before they are due, see schedule), handed in through Carmen. Late assignments are only accepted if extensions are requested and granted, and are penalized 20% on a per-question basis, so try to submit as many questions as possible on time.
• A final project (30% of grade), with the goal of gaining experience applying the techniques presented in class to real-world datasets. A typical individual project will compare predictions of two or more learning techniques on a novel or existing dataset, with one technique serving as a baseline and one serving as a test case. Students may work individually or in groups, but group work should involve proportionately more substantial development or experimentation than individual projects. It is a good idea to discuss your planned project with the instructor to get feedback. The final project report should be about 4 pages long (11 point, double-spaced, 1-inch margins) and is due after the end of instruction. The report should describe (1) the problem you are solving, (2) the data is being used, (3) the techniques you are applying, (4) the results and (5) some analysis of why the results came out as they did. Project reports and project code will be handed in through Carmen. In the case of group projects, each group member should hand in a separate report that focuses on their individual contribution.

Attendance and active participation often impacts your performance in a meaningful way, so it will be beneficial for you to attend this course synchronously as much as possible. The lecture slides will be posted on CarmenCanvas, so if you do miss a lecture, you are expected to view the missed material before the next lecture.

Faculty feedback and response time:

• Assignments: you can generally expect feedback within 7 days.
• Email: I will reply to e-mails within 24 hours on work days.
• Discussion board: I will ceck and reply to messages in the discussion boards within 24 hours on work days.

Grading scale: OSU standard scheme

A	A-	B+	B	B-	C+	C	C-	D+	D
93%+	90%+	87%+	83%+	80%+	77%+	73%+	70%+	67%+	60%+

Students with Disabilities: The University strives to make all learning experiences as accessible as possible. If you anticipate or experience academic barriers based on your disability (including mental health, chronic or temporary medical conditions), please let me know immediately so that we can privately discuss options. To establish reasonable accommodations, I may request that you register with Student Life Disability Services. After registration, make arrangements with me as soon as possible to discuss your accommodations so that they may be implemented in a timely fashion. SLDS contact information: slds@osu.edu; 614-292-3307; slds.osu.edu; 098 Baker Hall, 113 W. 12th Avenue.

Academic Misconduct: It is the responsibility of the Committee on Academic Misconduct to investigate or establish procedures for the investigation of all reported cases of student academic misconduct. The term "academic misconduct" includes all forms of student academic misconduct wherever committed; illustrated by, but not limited to, cases of plagiarism and dishonest practices in connection with examinations. Instructors shall report all instances of alleged academic misconduct to the committee (Faculty Rule 3335-5-487). For additional information, see the Code of Student Conduct http://studentlife.osu.edu/csc/.

Mental Health Services: As a student you may experience a range of issues that can cause barriers to learning, such as strained relationships, increased anxiety, alcohol/drug problems, feeling down, difficulty concentrating and/or lack of motivation. These mental health concerns or stressful events may lead to diminished academic performance or reduce a student's ability to participate in daily activities. The Ohio State University offers services to assist you with addressing these and other concerns you may be experiencing. If you or someone you know are suffering from any of the aforementioned conditions, you can learn more about the broad range of confidential mental health services available on campus via the Office of Student Life's Counseling and Consultation Service (CCS) by visiting ccs.osu.edu or calling 614-292-5766. CCS is located on the 4th Floor of the Younkin Success Center and 10th Floor of Lincoln Tower. You can reach an on call counselor when CCS is closed at 614-292-5766 and 24 hour emergency help is also available through the 24/7 National Suicide Prevention Hotline at 1-800-273-TALK or at suicidepreventionlifeline.org.

Sexual Misconduct / Relationship Violence: Title IX makes it clear that violence and harassment based on sex and gender are Civil Rights offenses subject to the same kinds of accountability and the same kinds of support applied to offenses against other protected categories (e.g., race). If you or someone you know has been sexually harassed or assaulted, you may find the appropriate resources at http://titleix.osu.edu or by contacting the Ohio State Title IX Coordinator, Kellie Brennan, at titleix@osu.edu.

Diversity: The Ohio State University affirms the importance and value of diversity in the student body. Our programs and curricula reflect our multicultural society and global economy and seek to provide opportunities for students to learn more about persons who are different from them. We are committed to maintaining a community that recognizes and values the inherent worth and dignity of every person; fosters sensitivity, understanding, and mutual respect among each member of our community; and encourages each individual to strive to reach his or her own potential. Discrimination against any individual based upon protected status, which is defined as age, color, disability, gender identity or expression, national origin, race, religion, sex, sexual orientation, or veteran status, is prohibited.