Date |
Lecture Topic |
Read |
Assignment Due |
Discussion Section |
Jan |
|
|||
20 |
Course Overview, intro to supervised learning: k-NN |
ESL 2 |
|
|
22 |
Overview of some key concepts in machine learning |
ESL 2 PRML 1.2-1.4 |
|
|
27 |
No Class:
Snow |
|
26: probability review |
|
29 |
Linear models for regression: |
PRML 3.1 |
A1: k-NN |
|
Feb |
|
|||
3 |
Bayesian linear regression |
PRML 3.3 |
2: linear algebra |
|
5 |
Bias/variance, sequential learning |
PRML 3.2 |
|
|
10 |
No Class:
Snow |
9: Bayesian linear regression |
||
12 |
Linear models for classification |
PRML 4.1 |
A2: regression |
|
17 |
No Class: substitute Monday schedule |
|
|
17: linear classification |
19 |
Perceptron, Logistic regression |
PRML 4.2, 4.3 |
|
|
24 |
Logistic regression |
A3: classification |
23: TBA |
|
26 |
Support vector machines for classification |
PRML 7.1 ESL 12 |
|
|
Mar |
|
|||
3 |
Kernel methods |
PRML 6.1, 6.2, 7.1 |
|
2: kernel methods |
5 |
Kernel methods continued |
PRML 6.3, 6.4 |
|
|
8-15 |
No Class: spring recess |
|
|
|
17 |
review |
A4: kernel methods |
16: review |
|
19 |
Midterm: in class |
|
|
|
24 |
K-means clustering, EM |
PRML 9 |
23: midterm solutions |
|
26 |
Gaussian mixtures, EM |
PRML 9 |
|
|
31 |
Combining methods: boosting, bagging, AdaBoost |
PRML 14 ESL 10 |
30: EM, mixture of Bernoulli |
|
Apr |
||||
2 |
Combining methods: trees, forests, mixtures |
ESL 15-16 |
|
|
7 |
Graphical models, conditional independence |
PRML 8.1-8.2 |
A5: k-means, EM |
6: decision trees |
9 |
Markov Random Fields |
PRML 8.3 |
|
|
14 |
Inference algorithms for graphical models |
PRML 8.4 |
|
13: graphical models |
16 |
Inference algorithms for graphical models |
PRML 8.4 |
|
|
21 |
Sequential data: hidden Markov models |
PRML 12 |
|
20: exact inference |
23 |
Dimensionality reduction |
PRML 13 |
A6: TBA |
|
28 |
Neural networks |
PRML 5 |
27: review |
|
30 |
State-of-the-art, course wrap-up |
|
||
May |
|
|||
6 |
Final exam |
|
|
|