Clay Scott - Section 1: MW 10:30--12:00, 1571 GGBL
Salimeh Yasaei Sekeh - Section 2: MW 17:00-18:30, 2505 GGBL
Office Hours:
**Clay Scott : Monday 1:00 - 2:30 PM in EECS 4433
Salimeh Yasaei Sekeh: Tuesday 13:30-15:00 in EECS 3115
GSIs:
Aniket Deshmukh: Wednesday 1:00 - 2:30 PM tentatively in EECS 3312, table 4
Amanda Bower: Thursday 2:30 - 4:00 PM tentatively in EECS 3312, table 2
Yun Wei: Wednesday 3:30 - 5:00 PM tentatively in EECS 1222
Required text: None.
Recommended texts: (on reserve at the Art, Architecture, and Engineering Library)
- Murphy, Machine Learning: A Probabilistic Perspective, MIT Press, 2012, available online here or here to UM users.
- Hastie, Tibshirani, and Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer, Second Edition, pdf available for download This book is also available online to UM users, who may purchase a $25 print version by clicking on the "buy now" link from the online book.
- Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
- Mohri, Rostamizadeh, and Talwalkar, Foundations of Machine Learning, MIT Press, 2012, available online here.
- Duda, Hart, and Stork, Pattern Classification, Wiley, 2001, available online to UM users.
Additional references:
- Scholkopf and Smola, Learning with Kernels, MIT Press, 2002, available online . to UM users.
- Mardia, Kent, and Bibby, Multivariate Analysis, Academic Press, 1979 (good for PCA, MDS, and factor analysis).
- Boyd and Vandenberghe, Convex Optimization, Cambridge University Press, 2004, pdf available for download and also available online to UM users (only 7 users at a time).
- Shalev-Shwartz and Ben-David, Understanding machine learning: from theory to algorithms, Cambridge University Press, 2014.
- Sutton and Barto, Reinforcement Learning: An Introduction, MIT Press, 1998, available online to UM users.
- DasGupta, Probability for Statistics and Machine Learning, Springer 2011 available online
- Visual linear algebra videos, online 3Blue1Brown channel
Prerequisites: (the current formal prerequisite is currently listed as EECS 492, Artificial Intelligence, but this is inaccurate)
- Probability: jointly distributed random variables, multivariate densities and mass functions, expectation, independence, conditional distributions, Bayes rule, the multivariate normal distribution (e.g. EECS 501).
- Linear algebra: rank, nullity, linear independence, inner products, orthogonality, positive (semi-) definite matrices, eigenvalue decompositions (e.g. EECS 551, MATH 417).
- Multivariable calculus: partial derivatives, gradients, chain rule
- Programming skills in Matlab and Python (optional).
- It is expected that students will have a good working knowledge of these topics. Students with most but not all of this background should be able to catch up during the semester with some additional effort. Certain topics will be briefly reviewed.
Homework: 35%, submission via gradescope. Lowest 1 dropped.
Midterm exam 1: 20%, Thursday Oct. 25, 6:30-8:30 pm, Locations: TBA
Midterm exam 2: 20%, Thursday Dec. 6, 6:30-8:30 pm, Locations: TBA
Project: 25%
Extra credit: 5-10% to students who answer questions in Piazza and significantly enhance the course experience through their contributions.
Project proposal submission: due Wednesday, Oct. 31, at 5:00 pm, reviews due Wednesday, Nov. 7, at 5:00 pm. Final project report: due Friday, Dec. 14, at 5:00 pm, reviews due Tuesday, Dec. 18, at 5:00 pm.
Details:
Homeworks:
Homeworks will be assigned bi-weekly. Applications will be developed through programming exercises, including face recognition, spam filtering, handwritten digit recognition, image compression, and image segmentation. MATLAB and Python are the supported languages in the course. You must complete your programming assignments in one of these two languages.
Exam: You may use two cheat sheets (front and back), and no other materials are allowed. Please notify us the first week of class if you have a conflict.
Final Project:
There will be a final project. You will be asked to form groups of maximum 4. The project must explore a methodology or application not covered in the lectures. You will be asked to select a paper on a methodology not covered in class, and implement the method. You will grade each others projects using Canvas's peer grading feature.
Gradescope Entry Code:
MG2XEE, use this code to add the course to your account.
Piazza:
Most questions you have about the course, both logistical and technical, should be posted to Piazza. Questions about how to solve homework problems are encouraged, but responses should provide hints as opposed to detailed answers. You may indicate that your questions is for instructors only your question is of a sensitive nature or may disclose solutions to the class.
Standards of Conduct
Arrive to class on time. If you must enter a class after lecture has clearly begun, please do so quietly.
Focus on class material during class time. Sleeping, doing work for another class, checking email, and exploring the internet are unacceptable and can be disruptive.
Only use personal electronic devices during class for viewing or taking notes. If you elect to use a laptop during class, please type very quietly. Few things are more annoying than sitting next to someone who is pounding on their keyboard during a lecture.
Refrain from eating during class.
Avoid audible and visible signs of restlessness. These are both rude and disruptive to the rest of the class.
Don't pack your bags to leave until the instructor has dismissed class. Thank you.
Collaboration on homeworks:
Each student will prepare the final write-up/coding of his or her homework solutions without reference to any other person or source, aside from the student's own notes or scrap work. Students may consult classmates for the purpose of brainstorming, but not for obtaining the details of solutions. Under no circumstances may you copy solutions or code from a classmate or other source.
Academic Integrity
All undergraduate and graduate students are expected to abide by the College of Engineering Honor Code as stated in the Student Handbook and the Honor Code Pamphlet .
Students with Disabilities
Any student with a documented disability needing academic adjustments or accommodations is requested to speak with me during the first two weeks of class. All discussions will remain confidential.
Student Mental Health and Wellbeing
The University of Michigan is committed to advancing the mental health and wellbeing of its students. If you or someone you know is feeling overwhelmed, depressed, and/or in need of support, services are available. For help, contact Counseling and Psychological Services (CAPS) at (734) 764-8312 and https://caps.umich.edu/. during and after hours, on weekends and holidays, or through its counselors physically located in schools on both North and Central Campus. You may also consult University Health Service (UHS) at (734) 764-8320 and https://www.uhs.umich.edu/mentalhealthsvcs, or for alcohol or drug concerns, see https://www.uhs.umich.edu/aodresources. For a listing of other mental health resources available on and off campus, visit: http://umich.edu/~mhealth.
Equal opportunity
The Faculty of the COE are committed to a policy of equal opportunity for all persons and do not discriminate on the basis of race, color, national origin, age, marital status, sex, sexual orientation, gender identity, gender expression, disability, religion, height, weight, or veteran status. Please feel free to contact your instructor with any problem, concern, or suggestion. We ask that all students treat each other with respect.