Change in deadline and weekly update for FYS-ST3155/4155

Dear All, first, thx a million for heroic efforts with project 1. We really appreciate this and plan to come with feedback by the end of next week or at latest the beginning of the week thereafter. 

Since some of you experienced problems yesterday evening with handing in, we extended the deadline to today at 23.59 (lack of registration plus minor technical problems). If you have already handed in and wish to perfect your delivery, please feel free to do so. So, the deadline is today at 23.59.

Else, project 2 will be available by the end of the day and deals with neural networks (building a code for an MLP) and comparing classification and regression analysis with your existing linear regression codes from project 1 (including the analysis of the results) and logistic regression. 

We will thus end up with having programmed three central approaches to supervised learning. 

The lectures this week will also focus on building an MLP code, see for example https://compphysics.github.io/MachineLearning/doc/pub/NeuralNet/html/NeuralNet-bs.html

and the discussion of the back propagation algorithm. We will also bring up again how to code gradient descent methods and repeat parts of the logistic regression approach needed for project 2. This material can be found in   https://compphysics.github.io/MachineLearning/doc/pub/Splines/html/Splines-bs.html  and https://compphysics.github.io/MachineLearning/doc/pub/LogReg/html/LogReg-bs.html , respectively. Alternatively, chapters 4 and 11 of Hastie et al are also useful. 

Else, Geron's text at https://github.com/CompPhysics/MachineLearning/blob/master/doc/Textbooks/TensorflowML.pdf

covers many of these topics with an emphasis on scikit-learn and tensorflow in chapters 4, 9, 10 and 11. 

Best wishes to you all and thx again for many excellent projects.

Morten