CSE 4693/6693 Introduction to Machine Learning

This post is intended for preview purposes regarding course selection. Please note that the finalized syllabus may undergo changes.

Tentative Course Schedule

This schedule is subject to change depending on the progress of the course

1Course IntroductionQuiz 0: Pre-course Survey
2Fundamental: Formulation of ML task, Classification/Regression
3Fundamental: Formulation of ML task, Classification/Regression
4Fundamental: Analytic Methods for Regression
5Fundamental: Analytic Methods for RegressionQuiz 1
6Fundamental: Analytic Methods for Regressionrelease: HW 1
Project: Group and Topic
7Fundamental: Gradient Methods for Regression
8Fundamental: Logistic method for Classification
9Fundamental: Logistic method for ClassificationQuiz 2
10Probabilistic: Bayes RuleHW 1
11Probabilistic: Bayes RuleProject: Proposal
12Project Presentation
13Project Presentation
14Probabilistic: Bayes Rule
15Probabilistic: Bayes RuleQuiz 4
16Probabilistic: Bayes RuleExplain HW1, Midterm, Quiz 4
17Probabilistic: Bayes Rule
18Probabilistic: Bayes Rulerelease: HW 2
Project: Mid-point progress check
19Probabilistic: Bayes Rule
20Advance: Gaussian Process
21Advance: Gaussian ProcessQuiz 5
22Advance: Bayesian OptimizationHW 2
23Project Presentation
24Project Presentation
25Project Presentation
26Final Report Due


  • 25% In-Class Quiz
    • 2 graded surveys (5% = 2 * 2.5%)
    • 4 graded quizzes (20% = 4 * 5%)
  • 20% Homework (10% * 2)
  • 15% Midterm
  • 40% Group Project
    • topic selection and team building, 5%
    • mid-term presentation, 10%
    • mid-point check, 5%
    • final presentation, 20%

10 pt Normal Grade Mode

Letter GradeRange
A100% to 90%
B< 90% to 80%
C< 80% to 70%
D< 70% to 60%
F< 60% to 0%

Reference Books

  • [Intro] Murphy, Kevin P. Probabilistic machine learning: an introduction. MIT press, 2022.
  • [Adv] Murphy, Kevin P. Probabilistic machine learning: Advanced topics. MIT press, 2022.
  • [Applied] Rafatirad, Setareh, Houman Homayoun, Zhiqian Chen, and Sai Manoj Pudukotai Dinakarrao. Machine Learning for Computer Scientists and Data Analysts: From an Applied Perspective. Springer Nature, 2022.
  • [Hands-on] Géron, Aurélien. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. " O’Reilly Media, Inc.", 2022.
  • [IP] Integer programming (2021) Laurence A. Wolsey
  • [AP]Cormen, Thomas H., Charles E. Leiserson, Ronald L. Rivest, and Clifford Stein. Introduction to algorithms. MIT press, 2022.

Examinations and Assignments

All assignments must have your name, student ID and course name/ number. Examinations will heavily emphasize the conceptual understanding of the material. No make-up exams will be given for any other reason than those approved by the college office (serious illness, medical emergency). The exam format will be a mixture of multiple-choice questions and short/long answer questions. If you do not think that your test was graded appropriately, you need to send a valid written explanation for the requested change. This must be done within three days from the date the test was returned to you.

Late Submission Policy

Assignments are required to be submitted by the specified deadlines. Subsequent to the deadline, a penalty of 1% will be deducted from the total score for each hour past the due time, up to a maximum deduction of 50%. If an assignment is submitted after the in-class homework explanation (typically occurring 1-2 weeks post-deadline), submissions will not be accepted, resulting in a score of 0 for the assignment.

Assistant Prof.

My research interests include graph learningwith particular interest in graph dynamics.