Lecture 1. Supervised Learning 1
Learning Goals: You should know the concepts and basic mathematics of Linear Regression, Least squares optimization, overfitting/underfitting, the bias-variance tradeoff, cross-validation, regularization, k-nearest neighbor regression/classification. You should also be able to run and make modifications to basic matlab and python (scikit-learn) code for such algorithms.
Lecture01slides.pdf Download Lecture01slides.pdf
Lecture01 Video:
Also available via youtube: https://youtu.be/JF6BugAf0wA
Links to an external site.
and with subtitles via Canvas Studio here
Reading Assignment (this refers to the book Machine Learning (Links to an external site.) by Lindholm et al):
- Ch 2.1 and 2.2
- Ch 3.1 and 3.3
- Ch 4.1-4.4
- Ch 5.1-5.3 (numbering has changed, therefore Ch 5.3 is now also included)
Code used in the lecture (please don't worry about the unlogical naming of some of these files...)
- crazyflie_matlab.zip Download crazyflie_matlab.zip - polynomial regression, matlab
- lec3_cosinus.ipynb Links to an external site. - overfitting and crossvalidation, google colab
- lec3_ridge.ipynb Links to an external site. - decreasing overfitting problem with ridge regularisation, google colab
- knnfig.m Download knnfig.m - knn, matlab
- iris.m Download iris.m - knn on flower example, matlab