Welcome to the CMSC 726 course webpage for Fall 2019.
Review Probability, Linear Algebra and Convex Analysis.
Lecture 1 (8/27): Overview+ Prerequisites Quiz
Lecture 2 (8/29): Linear Regression
Lecture 3 (9/3): Programming Overview + Make-up quiz
Lecture 4 (9/5): No Lecture
Lecture 5 (9/10): Gradient Descent + Stochastic Gradient
Lecture 5 (9/12): Gradient Descent Convergence + Maximum Likelihood Estimation
Lecture 6 (9/17): Maximum Likelihood + Logistic Regression
Lecture 7 (9/19): Logistic Regression + Multi-label Classification
Lecture 8 (9/24): Convex Optimization, Lagrange Multipliers
Lecture 9 (9/25): KKT and Margins
Lecture 10 (10/1): Support Vector Machines + Hinge Loss
Lecture 11 (10/3): Soft SVM+ Coordinate Block Descent
Lecture 12 (10/8): Kernels
Lecture 13 (10/10): Project Disscusiion + Neural Networks
Lecture 14 (10/15): Deep Learning + Non-convex Optimization
Lecture 15 (10/17):MLP, Backpropagation
Lecture 16 (10/22): Vanishing Gradients, ResNet, Higher Order Derivatives
Lecture 17 (10/24): Robustness and Adversarial Examples
Lecture 18 (10/29): Midterm
Lecture 20 (10/31): PAC Learning + Uniform Convergence
Lecture 21 (11/5): Hoeffding Inequality + Finite Hypothesis Class
Lecture 22 (11/7): VC Dimension
Lecture 23 (11/12):Expectation-Maximization
Lecture 24 (11/14):Expectation-Maximization
Lecture 25 (11/19):KL Divergence + Variational AutoEncoders (VAEs)
Lecture 26 (11/21):Optimization of VAEs
Lecture 27 (11/26): Generative Adversarial Networks (GANs)
Lecture 28 (12/3): Principal Component Analysis (PCA)
Lecture 29 (12/5): Final presentations