| Moon's day | Woden' s day | Frigga's day |
|---|
|
Jan 9 |
|
Prolegomena. Course introduction
Slides |
|
|
|
Jan 11 |
|
Basic ML terminology with example
Slides |
|
|
|
Jan 13 |
|
Lab: Python libraries |
|
|
| |
|
Jan 18 |
|
The nature of data. From object to vectors
Slides |
|
|
|
Jan 20 |
|
K nearest neighbors
Slides |
|
|
|
Jan 23 |
|
Linear regression. Simple linear regression and ordinary least squares
Slides |
|
|
|
Jan 25 |
|
Lab: Linear (and related) regression techniques |
|
|
|
Jan 27 |
|
Newton's method and gradient descent
Slides |
|
|
|
Jan 30 |
|
Continuing gradient descent |
|
|
|
Feb 1 |
|
Training regression using gradient descent
Slides |
|
|
|
Feb 3 |
|
Logistic regression. From linear regression to classification
Slides |
|
|
|
Feb 6 |
|
Lab: Applying logistic regression |
|
|
|
Feb 8 |
|
Training logistic regression
Slides |
|
|
|
Feb 10 |
|
Gaussian mixture models Probability and distributions
Slides |
|
|
|
Feb 13 |
|
Lab: From histograms to Gaussians |
|
|
|
|
Feb 17 |
|
Expectation-maximization |
|
|
| |
|
Feb 22 |
|
Support vector machines. Linear programming |
|
|
|
|
Feb 27 |
|
Lab: Support vector classification |
|
|
|
|
| |
|
|
| |
|
|
|
Mar 20 |
|
Principal component analysis. PCA concepts
Slides |
|
|
|
Mar 22 |
|
Lab: PCAs and facial recognition |
|
|
|
Mar 24 |
|
Eigenvectors and eigenvalues |
|
|
| |
|
Mar 29 |
|
Neural nets. The perceptron model, multilayer perceptrons |
|
|
|
|
Apr 3 |
|
Perceptron training |
|
|
|
Apr 5 |
|
The feed-forward and back-propogatio algorithma |
|
|
|
|
Apr 10 |
|
Deap learning: CNNs |
|
|
|
Apr 12 |
|
Deep learning: RNNs |
|
|
|
Apr 14 |
|
Lab: Deep learning |
|
|
| |
|
|
| |
|
|