FYS-STK3155/4155 plans for week 36

Dear all, again, we hope this week started the best possible way. What follows is the weekly digest from last week with plans for this week.

Last week we continued our discussion of Linear regression with an emphasis on ordinary least squares.

We used last Thursday to remind ourselves about some basic elements of statistics and statistical analysis, such as quantities like the mean value, variance, standard deviation and the covariance. Parts of this material can be found under the slides on 'elements of probability theory' https://compphysics.github.io/MachineLearning/doc/pub/Statistics/html/Statistics.html and the beginning of the slides on Bayesian statistics https://compphysics.github.io/MachineLearning/doc/pub/Bayesian/html/Bayesian.html (these slides are under heavy revision).

We discussed also several examples on how to deal with different data sets (fitting and housing data). We started with a discussion of Ridge regression on Friday and started to scratch the surface of the bias-variance tradeoff topic. 

We continue this week with Ridge Regression and the Bias-Variance tradeoff, as well as Lasso regression and discuss their mathematics and the interpretations which can be made. All material we will discuss is covered by the Regression slides

https://compphysics.github.io/MachineLearning/doc/pub/Regression/html/Regression.html

If we get time we will also start discussing resamplling techniques like the bootstrap and cross-validation.  Chapter 3 of Hastie et al covers much of the material we will discuss (sections 3.1-3.4). Model assessment, cross-validation, the bias-variance tradeoff is covered by chapter 7 (7-1-7.6 and 7.10-7.11). See https://github.com/CompPhysics/MachineLearning/blob/master/doc/Textbooks/elementsstat.pdf or download the text from Springer's weblink (using your UiO username). 

At the lab today you can obviously start working with project 1 or look at exercise 4  which contains many of the elements you will code in project 1 (I corrected some of the text since it was not clear enough). I will solve exercise 5 during the lectures this week.  

Best wishes to you all,

Morten, Lucas, Hanna and Stian