CMSC 422 (Section 0201): Introduction to Machine Learning

University of Maryland, College Park, Spring 2022
Instructor: Soheil Feizi

Welcome to the CMSC 422 course webpage for Spring 2022.

CMSC 422 (Section 0201) is currently being taught by Soheil Feizi. See UMD Web Accessibility.

Announcements

  • Lecture 1 (1/25): Welcome to Machine Learning + ERMs

  • Lecture 4 (1/27): Decision Trees

    • Reading: Chapter 1 of the text book

    • Slides

  • Lecture 3 (2/1): Nearest Neighbor Classification

    • Reading: Chapter 3 of the text book

    • Slides

  • Lecture 4 (2/3):Perceptron

    • Reading: Chapter 4 of the text book

    • Slides

  • Lecture 5 (2/8): Convergence Analysis of Perceptron

  • Lecture 6 (2/10): Linear Classifiers, Gradient Descent and Hinge Loss

  • Lecture 7 (2/15): Gradient Descent Part II

    • Reading: Chapter 7 of the text book

    • Slides

  • Lecture 8 (2/17): GD (part III)+ Probabilistic View of ML, Naive Bayes

    • Reading: Chapter 9 of the text book

    • Slides

  • Lecture 9 (2/22): Review of Probability, Linear Algebra and Convex Analysis

  • Lecture 10 (2/24): Review of Probability, Linear Algebra and Convex Analysis

  • Lecture 11 (3/1): Probabilistic View of ML, Naive Bayes

    • Reading: Chapter 9 of the text book

    • Slides

  • Lecture 12 (3/3): Midterm

  • Lecture 13 (3/8): Logistic Regression + Multi-label Classification

  • Lecture 14 (3/10): Neural Networks

    • Slides

    • Reading: Chapter 10 of the text book

  • Lecture 15 (3/15): Nonlinear Regression + Back Propagation

    • Slides

    • Reading: Chapter 10 of the text book

  • Lecture 16 (3/17): Back Propagation

    • Slides

    • Reading: Chapter 10 of the text book

  • Lecture 17 (3/29): Vanishing Gradients, Multi Label Classification, Momentum method

    • Slides

    • Reading: Chapter 10 of the text book

  • Lecture 18 (3/31): Adversarial Robustness + Recurrent Neural Networks

  • Lecture 19 (4/5): Unsupervised Learning + K-Means

  • Lecture 20 (4/7): PCA

  • Lecture 21 (4/12): PCA analysis

  • Lecture 22 (4/14): AutoEncoders

    • Slides

    • Reading: Chapter 11 of the text book

  • Lecture 23 (4/18): Kernels

    • Slides

    • Reading: Chapter 11 of the text book

  • Lecture 24 (4/21): Kernels II

    • Slides

    • Reading: Chapter 11 of the text book

  • Lecture 25 (4/26): SVMs

    • Slides

    • Reading: Chapter 7 of the text book

  • Lecture 26 (4/28): SVMs II + KKT Conditions

    • Slides

    • Reading: Chapter 7 of the text book

  • Lecture 27 (5/3): SVMs III + Course Review

  • Lecture 28 (5/5): Final Presentations I

  • Lecture 29 (5/10): Final Presentations II