B Machine Learning (COMP-652 and ECSE-608)
Machine Learning (COMP-652 and ECSE-608)
Winter 2016

Lecture Schedule

Date Topic Materials
Jan.12 Introduction. Linear models. Lecture 1 slides
Bishop, Sec. 1.1, 3.1, 3.2 (or equivalent)
If you need to catch up on the math, a brief probability review and linear algebra and matrix calculus review from Stanford University; also, Bishop appendix B,C.
Jan.14 More on linear models. Overfitting. Regularization. Lecture 2 slides
Bishop, Sec. 3.1, 3.2
Jan.19 More on Bayesian and maximum likelihood fitting Lecture 3 slides

Jan.21 Bayesian regression. Logistic regression Lecture 4 slides
Jan.26 More on logistic regression. Kernels. Lecture 5 slides
Jan.28 More on kernels. Supoort vector machines Lecture 6 slides
Feb. 2 Active learning Lecture 7 slides
Feb. 4 Learning with structured data. Introduction to graphical models via mixture models. Lecture 8 slides
Feb. 9 Guest lecture (TBA) Lecture 9 slides
Feb.11 Guest lecture (TBA) Lecture 10 slides
Feb.16 Representational power of directed graphical models. Inference methods Lecture 11 slides
Feb.18 Learning methods for graphical models. Latent variables. Lecture 12 slides
Feb.23 Undirected graphical models. Representational power. Lecture 13 slides
Feb.25 Inference and learning in undirected graphical models Lecture 14 slides
Mar. 8 Boltzmann machines. Deep belief networks Lecture 15 slides
Mar.10 Unsupervised learning: a latent variable perspective Lecture 16 slides
Mar.15 Dimensionality reduction: PCA, kernel PCA, autoencoders. Lecture 17 slides
Mar.17 More on autoencoders. Variational inference Lecture 18 slides
Mar.22 Time series analysis. Latent variable models for time series analysis. Lecture 19 slides
Mar.24 Spectral methods for time series. Lecture 20 slides
Mar.29 Non-parametric methods for time series (and other structured) data Lecture 21 slides
Mar.31 In-class midterm exam
Apr. 5 Monte Carlo vs temporal-difference methods for time series. Lecture 22 slides
Apr. 7 Reinforcement learning. Markov Decision Processes and Bellman equations Lecture 23 slides
Apr.12 Function approximation methods for reinforcement learning Lecture 24 slides
Apr.14 The problem of optimal control. Exploration-exploitation trade-off. Value-based and policy-based methods. Lecture 25 slides