Sept 6 | Homework 1 is up (due before class on Tuesday, Sept 13) | HW1 |
Sept 13 | Homework 2 is up (due before midnight Sunday, Sept 25) | HW2 |
Sept 27 | Homework 3 is up (due before midnight Sunday, Oct 9) | HW3 |
Oct 10 | Homework 4 is up (due before midnight Sunday, Oct 23) | HW4 |
Oct 15 | Earlier midterms | 2015 2014 |
Oct 27 | Homework 5 is up (due before class Thursday, Nov 10) | HW5 |
Nov 10 | Homework 6 is up (due before class Thursday, Nov 24) | HW6 |
Nov 21 | Earlier midterms | 2015 |
Dec 3 | Midterm 2 | |
Week 1 | Iain Murray's cribsheet,
Sam Roweis' notes,
A short introduction to R ,
Plotting with ggplot2 Useful references: Review of probability and statistics (Stanford notes) , R Manual |
Week 2 | R Markdown: Tutorial 1 ,
Tutorial 2 (we will use this for the homeworks) Section 5 on eigenvalues of Richard Shewchuk's tutorial on the conjugate gradient method |
Week 3 | Complexity and big-O notation: Link 1 ,
Link 2
Link 3 This is a nice introduction to big-O notation Quicksort Knapsack problem (ignore the C code) The Needleman-Wunsch algorithm |
Week 4 | Clustering: Read Section 10.3 of An Introduction to Statistical Learning MLE for the multivariate Gaussian. See Sections 2 and 3 here . |
Week 5 |
MLE for the multivariate Gaussian. See Sections 2 and 3 here . Jensen's inequality here . Kullback-Liebler divergence (Page 2 here ). |
Week 6 |
Tony Jebara's' introduction to exponential family distributions. Jeff Bilmes' tutorial on the EM algorithm. If you're feeling ambitious, here is the original paper on the EM algorithm. Some project ideas here , I'll try to add to this. You can search for others on other course webpages. In general, make sure your project allows you to code up some non-trivial algorithm (rather than just use packages) |
Week 7 |
Some notes on gradient descent here .
This is also useful.
|
Week 9 |
Jeff Gills's introduction to MCMC. Andrieu et al.'s introduction to MCMC. Radford Neal, in rather more detail on MCMC. |