CMSC 726: Machine Learning

Welcome to the CMSC 726 course webpage for Fall 2019.

CMSC 726 is currently being taught by Soheil Feizi.

Announcements

• Review Probability, Linear Algebra and Convex Analysis.

• Lecture 1 (8/27): Overview+ Prerequisites Quiz

• Lecture 2 (8/29): Linear Regression

  • Reading: Section 9.2 of the text book + pages 1-11 of notes

• Lecture 3 (9/3): Programming Overview + Make-up quiz

• Lecture 4 (9/5): No Lecture

• Lecture 5 (9/10): Gradient Descent + Stochastic Gradient

  • Reading: pages 4-7 of notes

• Lecture 5 (9/12): Gradient Descent Convergence + Maximum Likelihood Estimation

  • Reading: Section 14.1 of the text book+ Section 3 of notes

• Lecture 6 (9/17): Maximum Likelihood + Logistic Regression

  • Reading: Section 9.3 of the text book+ part II of notes

• Lecture 7 (9/19): Logistic Regression + Multi-label Classification

  • Reading: Section 9.3 of the text book+ part II of notes

• Lecture 8 (9/24): Convex Optimization, Lagrange Multipliers

  • Reading: Section 5 of notes

• Lecture 9 (9/25): KKT and Margins

  • Reading: Part V of notes

• Lecture 10 (10/1): Support Vector Machines + Hinge Loss

  • Reading: Part V of notes

• Lecture 11 (10/3): Soft SVM+ Coordinate Block Descent

  • Reading: Section 9 of notes

• Lecture 12 (10/8): Kernels

  • Reading: Section 16 of the text book + Section 7 of notes

• Lecture 13 (10/10): Project Disscusiion + Neural Networks

  • Reading: Section 5 of notes

• Lecture 14 (10/15): Deep Learning + Non-convex Optimization

  • Reading: Section 20 from the text book.

• Lecture 15 (10/17):MLP, Backpropagation

  • Reading: Section 5 of notes.

• Lecture 16 (10/22): Vanishing Gradients, ResNet, Higher Order Derivatives

  • Reading: Section 5 of notes.

• Lecture 17 (10/24): Robustness and Adversarial Examples

  • Reading: paper

• Lecture 18 (10/29): Midterm

• Lecture 20 (10/31): PAC Learning + Uniform Convergence

  • Reading: Chapters 3 and 4 from the text book.

• Lecture 21 (11/5): Hoeffding Inequality + Finite Hypothesis Class

  • Reading: Chapters 3 and 4 from the text book.

• Lecture 22 (11/7): VC Dimension

  • Reading: Chapters 5 and 6 from the text book.

• Lecture 23 (11/12):Expectation-Maximization

  • Reading: notes and notes.

• Lecture 24 (11/14):Expectation-Maximization

  • Reading: notes and notes.

• Lecture 25 (11/19):KL Divergence + Variational AutoEncoders (VAEs)

  • Reading: VAE Tutorial

• Lecture 26 (11/21):Optimization of VAEs

  • Reading: VAE Tutorial

• Lecture 27 (11/26): Generative Adversarial Networks (GANs)

  • Reading: ref1 ref2

• Lecture 28 (12/3): Principal Component Analysis (PCA)

  • Reading: notes.

• Lecture 29 (12/5): Final presentations