Machine Learning (COMP-652 and ECSE-608)
Winter 2017

Lecture Schedule

Date Topic Materials
Jan. 5 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.10 More on linear models. Overfitting. Regularization. Lecture 2 slides
Bishop, Sec. 3.1, 3.2
Jan.12 More on Bayesian and maximum likelihood fitting. Logistic regression Lecture 3 slides

Bishop Sec. 3.3, 4.3 (or equivalent)
Jan.17 More on logistic regression. Introduction to kernels. Lecture 4 slides
Bishop, Sec. 6.1, 6.2
Jan.19 More on kernels. Introduction to Support vector machines. Lecture 5 slides
Bishop, Sec. 7.1

Jan.24 More on kernels. Supoort vector machines Lecture 6 slides
Bishop, Sec. 7.1
Jan.26 Active learning Lecture 7 slides
Jan.31 Learning with structured data. Introduction to graphical models via mixture models. Lecture 8 slides
Feb. 2 Representational power of directed graphical models. Inference methods Same slide deck as last lecture
Feb. 7 Hidden Markov Models: Inference and Learning Lecture 10 slides
Feb. 9 More on learning in directed graphical models Lecture 11 slides
Feb.14 No class (watch Tibshirani invited talk at NIPS)
Feb.16 Undirected graphical models Lecture 12 slides
Feb.21 Dimensionality reduction: PCA, kernel PCA, LLE Lecture 13 slides
Bishop 12.1, 12.3 (or equivalent)
Locally Linear Embeddings (optional)
Feb.23 Non-linear dimensionality reduction: auto-encoders Lecture 15 slides
Quoc Le tutorial on backpropagation and tutorial on autoencoders, convnets and recurrent nets (first part)
Mar. 7 Spectral methods for time series. Lecture 16 slides (thanks to B. Balle, A. Quattoni and X. Carrreras)
Machine Learning paper
Mar. 9 Learning dynamical systems: Bayesain updating, Kalman filters and friends Lecture 17 slides
Mar.14 Recurrent Neural Networks Lecture 18 slides
Quoc Le tutorial on backpropagation and tutorial on autoencoders, conv nets and deep nets (last part)
Mar.16 Method of moments, latent variable models, and tensors Lecture 19 slides
JMLR paper
Mar.21 Recap for midterm Solutions to 2016 midterm> (disucssed in class)
Mar.23 More recap Lecture 21 slides
Mar.28 In-class midterm exam Some examples of midteurm-style questions with solutions
Midterm from 2016
Mar.30 Generatice Adversarial Networks Lecture 22 slides
Apr. 4 Computational learning theory Lecture 23 slides
Apr. 6 Reinforcement learning for prediction Lecture 24 slides
Apr.11 Reinforcement learning for control Lecture 25 slides