Computer Science 446

Machine Learning

Spring 2021

Instructor: Dan Gildea office hours M/W 1-2pm

TAs:

Prereqs: Probability, Linear Algebra, Vector Calculus.

Homeworks

Lecture notes

Required text: Christopher M. Bishop, Pattern Recognition and Machine Learning.

The following are useful references in addition to the reading material assigned for each class:

  • Stuart Russell and Peter Norvig, Artificial Intelligence, A Modern Approach.
  • Trevor Hastie, Robert Tibshirani, Jerome Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction.
  • Larry Wasserman, All of Statistics, 2004.

Syllabus

Onwe will coverwhich means that after class you will understandif before class you have read
2/2 Regression and Classification constrained optimization, perceptron bishop 1.2, 1.4, app E
2/4 Logistic Regression stochastic gradient descent bishop 4.3
2/9 Backpropagation DP for gradient descent bishop 5.1, 5.2, 5.3
2/11 Deep Learning drop-out Krizhevsky 2012
2/16 Support Vectors max-margin bishop 3.1, 4.1
2/18 Support Vectors strong duality bishop 7.1
2/23 Support Vectors the kernel trick bishop 6.1, 6.2
2/25 Hidden Markov Models forward-backward bishop 13.2
3/2 Graphical Models bayes ball
3/4 Probabilistic Inference message passing bishop 8.4
3/9 Tree decomposition cyclic graphs koller and friedman
3/11 Tree decomposition cont'd vertex elimination
3/16 Review
3/18 Midterm
3/23 Midterm Solutions
3/25 Fairness in machine learning Kleinberg, Corbett-Davies
3/30 no class
4/1 Expectation Maximization L = Q + H + D bishop 9
4/6 Expectation Maximization mixture of gaussians bishop 9
4/8 EM for HMM minimum bayes risk
4/13 Sampling Markov Chain Monte Carlo bishop 11.2
4/15 Metropolis Hastings detailed balance bishop 11.2
4/20 Gibbs sampling annealing bishop 11.3
4/22 Learning Theory PAC Kearns and Vazirani
4/27 Gradient Descent SGD convergence Ruder 2016
4/29 GAN/VAE deep generative models Goodfellow et al. 2014, Kingma and Welling 2014
5/4 Reinforcement Learning q-learning sutton ch 3, 4.3, 4.4, 6.1, 6.5, 7.2, 11.1
5/6 Review come to class with questions!

Grading

  • Homeworks: 50%
  • Final exam: 30%
  • Midterm: 20%

gildea @ cs rochester edu
April 27, 2021