Spring 2007

- Homework 9
- Due Tuesday 5/1 in class
- Thrun et al., ch4 ex 1, 2, 4, 5

- Homework 8
- Due Tuesday 4/10 in class
- Bishop 4.18, Bishop 1995 7.9

- Homework 7
- Due Tuesday 3/20 in class
- Bishop 12.5, 12.7, K and V 3.1, 3.6

- Homework 6
- Due Tuesday 3/6 in class
- Bishop 9.11, 9.19, 11.13

- Homework 5
- Due Tuesday 2/27 before class
Implement EM fitting of a mixture of gaussians on the two-dimensional data set points.dat. You should try different numbers of mixtures, as well as tied vs. separate covariance matrices for each gaussian. Which model seems to fit the data best?

- Homework 4
- Due Tuesday 2/13 in class
- Bishop 5.1, 5,4, 5.7, 6.2, 6.11

- Homework 3
- Due Tuesday 2/6 in class
- Bishop 2.15, 4.10, 4.11
- Implement a naive bayes classifier with a Dirichlet prior to predict the party of a US representative from their voting record: voting2.dat. Experiment with different values for the prior parameters: what setting gives the highest classification rate?

- Homework 2
- Due Tuesday 1/30 in class
- Bayes nets: Prove that, given a network structure A->B->C, A is conditionally independent of C given B.
- Explaining away: Prove that, given a network structure A->B<-C, A is
**not**independent of C given B, and is independent when marginalizing over B. - Use Lagrange multipliers to derive the multinomial distribution over K possible outcomes that maximizes entropy.
- Bishop 1.32

- Homework 1
- Due Tuesday 1/23 in class
Bishop ex. 1.3, 1.5, 1.6, 1.11

gildea @ cs rochester edu April 17, 2007