CSE 353 Machine Learning
Fall 2025, SUNY Korea
Fall 2025, SUNY Korea
Instructor: Byungkon Kang
Classes: TTh 15:30 - 16:50 @A115
Office hours (@B421): M 13:00 - 15:00, W 10:00 - 12:00
Prerequisite: C or higher in CSE316
TA office hours (@ the CS commons, 4th floor of building B)
Ryangjin Lee: T,Th 13:30 - 15:30
This is a course designed to introduce basic concepts in machine learning.
By the end of this semester, students are expected to know the workings of vanilla ML algorithms: what are the basic mathematical models, what kind of problems can they solve, etc, as well as some of the (more recent) core deep learning concepts.
Experience in the following is most recommended:
Linear algebra
Probability/statistics
Optimization
Reading published research articles
There is no required textbook for this course. Instead, I will draw materials from the following list of books.
Richard O. Duda, Peter E. Hart, David G. Stork. "Pattern Classification". Wiley-Interscience, 2000. ISBN: 0471056693. (Good beginner's book)
Christopher M. Bishop, "Pattern Recognition and Machine Learning". Springer, 2011. ISBN: 0387310738. (Good intermediary material)
Kevin P. Murphy, "Machine Learning: A Probabilistic Perspective". The MIT Press, 2012. ISBN: 0262018020. (Better suited for advanced readers)
Ian Goodfellow, Yoshua Bengio, and Aaron Courville, "Deep Learning". The MIT Press, 2016. ISBN: 0262035618. (An HTML version can be found here)
It would be a good idea to purchase at least one reference textbook if you're serious about doing research in machine learning, but please do not acquire them illegally.
Some of the topics will be based on published papers, in which case a link to those papers will be given in the schedule below.
The following may be subject to change, so please check back regularly. The dates are in "Month/Day format".
To access the lecture slides, you'll need to have logged in with your stonybrook.edu account.
Week 1: Introduction to ML (8/26), Preliminary math (8/28)
Week 2: Maximum likelihood estimation (9/2), Bayesian parameter estimation (9/4)
Week 3: Logistic regression (9/9), k-nearest neighbor classifier (9/11, HW1 out - 9/12)
Week 4: Decision trees (9/16), Naive Bayes (9/18, HW1 due - 9/19)
Week 5: Model selection + Generative & discriminative models (9/23), Clustering (9/25, HW2 out)
Week 6: Principal component analysis (9/30), Midterm 1 (10/2, HW2 due)
Week 7: No classes. Happy Chuseok!(10/7), (10/11)
Week 8: Support vector machines (10/14, 10/16)
Week 9: Kernel trick (10/21, HW3 out), Reinforcement learning (10/23)
Week 10: Reinforcement learning (10/28, HW3 due, HW4 out), Neural networks (10/30)
Week 11: Neural networks (11/4), Midterm 2 (11/6, HW4 due)
Week 12: Convolutional neural networks (11/11, 11/13)
Week 13: Intro. to PyTorch (sample code: train.py, model.py, HW5 out) (11/18) Recurrent neural networks & Autoencoders (11/20)
Week 14: Deep generative models (GAN) (11/25), Deep generative models (FBM) (11/27, HW5 due)
Week 15: Extra deep learning topic (12/2, 12/4)
Final exam: 12/9, 15:15 - 17:45
Scribe (10% x 2 = 20%): Scribes are written summaries of class lectures. Each student should submit two scribes on topics of his/her choice.
Midterm exams (10% x 2 = 20%)
Homework assignments (6% x 5 = 30%): Five (5) assignments
Final exam (30%): Cumulative, but more emphasis on the remaining contents.
All assignments should be submitted to Brightspace. Any grading disputes must be made within 3 days of the release of scores.
Attendance is not explicitly part of your final grade, but missing more than 20% of the classes will automatically result in a grade of 'F'.
In case you need to be excused for illness (e.g., for make-up exams), you should
Notify me via email before the class, and
Bring in a doctor's note containing: the diagnosis, period of treatment, and the reason why you had to miss class.
Only exams will be available for make-ups.
Students should pursue their academic goals in an honest way that does not put you at an unfair advantage over other students. You are responsible for all work you submitted and representing other’s work as yours is always wrong. Faculty is required to report any suspected instance of academic dishonesty to the school. Regarding your homework, you are encouraged to discuss it with others, but you should write your own code. For more information please refer to http://www.stonybrook.edu/commcms/academic\_integrity/index.html.
Typing in a query to a virtual assistant software such as ChatGPT does not count as your own 'work'. Even the slightest use of these tools in any of your assignments will result in the immediate dismissal from class with a grade of 'F'. Any suspected students will be subjected to further investigations such as interviews, additional in-person assignments, etc..
If you have a physical, psychological, medical or learning disability that may impact your course work, please let the instructor know. Reasonable accommodation will be provided if necessary and appropriate. All information and documentation are confidential.
Stony Brook University expects students to respect the rights, privileges, and property of other people. Faculty are required to report to the Office of Judicial Affairs any disruptive behavior that interrupts their ability to teach, compromises the safety of the learning environment, or inhibits students' ability to learn. Faculty in the HSC Schools and the School of Medicine are required to follow their school-specific procedures.