| Moon's day | Woden' s day | Frigga's day |
|---|
| |
|
Jan 20 |
|
Introduction. General introduction to course |
|
|
|
Jan 22 |
|
A complete example |
|
|
|
Jan 25 |
|
The nature of data |
|
|
|
Jan 27 |
|
Lab activity: Introduction to Python data science libraries |
|
|
|
Jan 29 |
|
Probability and statistics. Probability spaces, probability density, random variables |
|
|
|
Feb 1 |
|
Sum and product rules, Bayes's theorem, statistics |
|
|
|
|
Feb 5 |
|
Models, data, and training |
KNN project assigned
|
|
|
Feb 8 |
|
Linear regression. Concepts |
|
|
|
Feb 10 |
|
Lab activity: Linear regression |
|
|
|
Feb 12 |
|
Algorithmic details |
|
|
|
Feb 15 |
|
GMMs and EM. Gaussian mixture models |
|
|
|
Feb 17 |
|
Lab activity: From histograms to Gaussians |
|
|
|
Feb 19 |
|
Expectation maximization |
KNN project due; GMM-EM project assigned
|
|
|
Feb 22 |
|
Lab activity: Training GMMs with EM |
|
|
|
|
|
Mar 1 |
|
Neural nets. General introduction |
|
|
|
Mar 3 |
|
Lab activity: Neural nets |
|
|
|
Mar 5 |
|
Perceptron training |
|
|
| |
|
|
Mar 12 |
|
Help on GMM-EM project |
|
|
|
Mar 15 |
|
Deriving back-propogation |
GMM-EM project due Mar 16
|
|
|
Mar 17 |
|
Deriving back-propogation, part 2 |
MLP project part 1 assigned
|
|
|
Mar 19 |
|
Variations on back-propogation |
|
|
|
Mar 22 |
|
Lab activity: Deep learning with TensorFlow |
|
|
|
Mar 24 |
|
Support vector machines. Concepts |
|
|
|
Mar 26 |
|
Lab activity: Classification using SVMs |
|
|
| |
|
|
| |
|
Apr 7 |
|
Principal component analysis. Concepts |
|
|
|
|
Apr 12 |
|
PCA algorithms |
SVN project due; PCA project assigned
|
|
|
Apr 14 |
|
Reinforcement learning. Concepts |
|
|
|
Apr 16 |
|
Lab activity: reinforcement learning |
|
|
| |
|
Apr 21 |
|
Ethics |
PCA project due
|
|
|
| |
|
|