menu MENU

EECS 498: Principles of Machine Learning, Fall 2022

Course Instructor: Prof. Laura Balzano, Prof. Qing Qu, Prof. Lei Ying

(listed in alpha beta order, please contact Prof. Qing Qu for more details)

Teaching Assistant: Alexander Ritchie

Title: Principles of Machine Learning

Course Time: Mon/Wed 1:30 PM – 3:00 PM,  3 credit hour

Office Hour: Wed 3:30 PM – 5:00 PM

Prerequisite: EECS 351, or EECS 301, or any linear algebra courses

Notice: This is an entry-level machine learning course targeted for senior undergraduate and junior master students. This course is a little bit more emphasis on mathematical principles in comparison to EECS 445. Students outside the ECE program interested in machine learning are welcome as well!

Overview: The class will cover basic principles in machine learning, such as unsupervised learning (e.g., clustering, mixture models, dimension reduction), supervised learning (e.g., regression, classification, neural networks & deep learning), and reinforcement learning. For each topic, key algorithmic ideas/intuitions and basic theoretical insights will be highlighted.

Course Materials: slides and videos will be accessed via Canvas (TBA). Tentative topics that will be covered in this course are supervised learning, unsupervised learning, and reinforcement learning:

  • Basics of probability, linear algebra, and optimization
  • Regression and linear prediction
  • Support vector machines and kernel methods
  • Deep neural networks
  • Dimension reduction: PCA, autoencoder
  • Clustering (Kmeans, Mixture of Gaussians, EM)
  • Representation learning: nonnegative matrix factorization, dictionary learning
  • Basics of Online/reinforcement learning

Assessment: (i) homework assignment (5 in total, 40%), (ii) mid-term exam (30%), (iii) Final project (30%)

Textbook: We recommend the following books and articles, although we will not follow them closely.

Related courses:

  • EECS 445. Introduction to Machine Learning
  • EECS 453. Applied Matrix Algorithms for Signal Processing, Data Analysis, and Machine Learning
  • EECS 505. Computational Data Science and Machine Learning
  • EECS 545. Machine Learning

Syllabus: (tentative)

WeekDate TopicContentsInstructorHomework, Review
Week-1-108/30IntroductionCourse overviewQing Qu 
Week-1-209/01Supervised LearningIntroduction to supervised learning, linear models, regularizationQing QuLinear Algebra Review 
Week-2-109/06Labor DayNo class  
Week-2-209/08Supervised LearningLogistic RegressionQing QuProbability Review, HW1 Release 
Week-3-109/13Supervised LearningLogistic Regression continued, optimization methodsQing Qu 
Week-3-209/15Supervised LearningOptimization methodsQing QuPython Review 
Week-4-109/20Supervised LearningLinear classification, support vector machine (SVM) IQing Qu 
Week-4-209/22Supervised LearningLinear classification, support vector machine (SVM) IIQing QuHW1 Due, HW2 Release 
Week-5-109/27Supervised LearningDual SVMQing Qu 
Week-5-209/29Supervised LearningNonlinear models, kernel methodsQing Qu 
Week-6-110/04Supervised LearningIntroduction to deep neural networks IQing Qu 
Week-6-210/06Supervised LearningIntroduction to deep neural networks IIQing QuHW2 Due,  HW3 Release  
Week-7-110/11Supervised LearningIntroduction to deep neural networks IIIQing Qu 
Week-7-210/13Unsupervised LearningIntroduction to unsupervised learning, clustering problem, K-meansQing Qu 
Week-8-110/18Fall Study DayNo class  
Week-8-210/20Unsupervised LearningK-means, mixtures of Gaussian, expectation maximizationQing Qu HW3 Due
Week-9-110/25Midterm ReviewMidterm ReviewQing Qu 
Week-9-210/27MidtermMidtermQing Qu 
Week-10-111/01Unsupervised LearningDimension reduction, PCAQing Qu 
Week-10-211/03Unsupervised LearningDimension reduction IIQing QuHW4 Release, Project Proposal Due
Week-11-111/08Unsupervised LearningRepresentation learning, matrix factorizationQing Qu 
Week-11-211/10Unsupervised LearningRepresentation learning, matrix factorizationQing Qu 
Week-12-111/15Unsupervised LearningAutoencoder, self-supervised learning, GANQing Qu 
Week-12-211/17Unsupervised LearningAutoencoder, self-supervised learning, GANQing Qu HW4 Due, HW5 Release 
Week-13-111/22Reinforcement LearningTBDLei Ying 
Week-13-211/24Thanksgivingno class  
Week-14-112/01Reinforcement LearningTBDLei Ying 
Week-14-212/03Reinforcement LearningTBDLei YingHW5 Due 
Week-15-1 12/06FinalFinal project preparationQing Qu
Week-15-2 12/08 FinalFinal project presentationQing Qu