Weekly plans and update for week 40

Hello everybody and thx so much for heroic efforts with project 1.

I have now posted the first iteration of project 2 and we will discuss this during tomorrow's and Friday's lectures. A git pull should give you all relevant files, or simply go to https://compphysics.github.io/MachineLearning/doc/web/course.html and scroll down to project 2.

The main aim of project two is to develop a feed forward neural network code for both classification and regression. We will discuss the development of such a code during the lectures tomorrow and Friday. The code examples and more can be found in the neural network slides at https://compphysics.github.io/MachineLearning/doc/pub/NeuralNet/html/NeuralNet.html

In the project we propose data sets for classification and regression, but if you would like to use other data sets which are closer to your research/interests, feel free to do so.

Last week we ended Friday's lecture with the derivation of the so-called back propagation algorithm. 

We start there tomorrow and dive thereafter into a discussion of how we can write a code for a neural network. 

Else, I am delayed with answering you concerning project 1 (in particular the CV with bias and variance). Several of you have asked about various aspects of project 1 and

I will try to answer as quickly as possible.

I may bring up some of these topics during the lectures this week.

However, in case you are struggling with the CV algo, in the revised version of the project you can also use the bootstrap resampling method. This is often easier to implement and easier to use when you do the bias-variance analysis.

Best wishes to you all,

Hanna, Lucas, Morten, Stain and ?yvind