CSCI 635: Introduction to Machine Learning (Online Synchronous)
(Fall 2024)

Personnel

Instructor: Haibo Yang, Assistant Professor, Dept. of Computing and Information Sciences Ph.D.
Contact: Rm 74-1073, hbycis@rit.edu
Time & Location: MoWeFr 1:00PM - 1:50PM (08/26/2024 - 12/09/2024),
Office Hours: Monday 1:50PM – 2:50PM
TA: Faseeh Ahmed Mohammad
TA Hours: Tuesday : 2:30 to 3:30

Course Description

An introduction to both foundational and modern machine learning theories and algorithms, and their application in classification and regression. Topics include: Mathematical background of machine learning (e.g. statistical analysis and visualization of data), Bayesian decision theory, parametric and nonparametric classification models (e.g., SVMs and Nearest Neighbor models) and neural network models (e.g. Convolutional, Recurrent, and Deep Neural Networks). Programming assignments are required.

Course Materials

Recommended Textbooks

  • Hastie, T., et al. (2009) The elements of statistical learning, 2nd Edition. Springer.
  • Charniak, E. (2019) An Introduction to Deep Learning.
    •

    Additional References

  • Francis Bach. (2023) Learning Theory from First Principles.
  • Ian Goodfellow, et al. (2016) Deep Learning, MIT press, 2016.
    •

    Prerequisites

    (CSCI-603 or CSCI-605 with a grade of B or better) or ((CSCI-243 or SWEN 262) and (MATH-251 or STAT-205)) or equivalent courses.

    Grading Policy

    Class Participation: 10%; Assignments: 40%; Project: 50%.

    Schedule

    Week/Start Topics Others
    1 (8/26) Machine learning, classification, regression Lec01,Lec02,Lec03
    2 (9/02) Linear models, Least Squares Lec04,Lec05
    3 (9/09) KNN, SVM Lec06,Lec07,Lec08,Lec09
    4 (9/16) Kernel Lec09,Lec10,Lec11
    5 (9/23) SVM, Kernel Lec12
    6 (09/30) Navie Bayes, Perceptron Learning, Neural Networks Lec13,Lec14,Lec15
    7 (10/07) Backpropagation Lec16,Lec17,Lec18
    8 (10/14) Bias,variance, regularization Lec19,Lec20
    9 (10/21) Decision Tree,ensembles Lec21,Lec22,Lec23
    10 (10/28) Project Proposal Presentations Pre-1,Pre-2,Pre-3
    11 (11/04) Unsupervised learning: clustering, K-means Lec24,Lec25,Lec26
    12 (11/11) EM, PCA Lec27,Lec28,Lec29
    -- (11/18) Self-supervised learning Lec30，Lec31
    13 (11/25) THANKSGIVING WEEK – NO CLASSES
    14 (12/02) Reinforcement learning
    15 (12/9) Finals

    Academic Integrity

    As an institution of higher learning, RIT expects students to behave honestly and ethically at all times, especially when submitting work for evaluation in conjunction with any course or degree requirement. The Golisano College of Computing and Information Sciences encourages all students to become familiar with the RIT Honor Code and with RIT's Academic Integrity Policy. Students may discuss assignments with others including classmates, tutors and SLI instructors. After any such discussions, students must discard all written notes/pictures/etc. Submitting any work written by others or as an unsanctioned team is considered an act of academic dishonesty. Team-developed work also must be created solely by the team members and not copied from others or other sources. Work copied from Github or other similar sources will be subject to prosecution for breach of academic integrity.