Plans for the week January 29-February 2

Dear all, we hope you've had a great weekend. Here are our plans for this week

Discussion of possible projects

Review of neural networks and automatic differentiation

Discussion of codes

Please do send to Morten (mhjensen@uio.no) by the end of Monday (January 29) whether you wish to present a tentative project description (1-3 slides, 5-10 mins presentations and discussions) during the first hour. 

As of now only two groups have responded that they would like to present their tentative projects.  We are planning to discuss various projects and in case you have not yet decided what you want to work on, this may be a good opportunity to get inspired and/or even join  a specific group.

Else, much of the material this week is similar to last week and we will discuss and review (for those of you who have written a neural network code) the basics of neural networks, with the back propagation algorithm and automatic differentiation as mathematical tools and algorithms.  The lecture slides are included here as a jupyter-notebook at https://github.com/CompPhysics/AdvancedMachineLearning/blob/main/doc/pub/week3/ipynb/week3.ipynb, with reading recommendations as well. The material on automatic differentiation will be discussed during during the lecture tomorrow on the whiteboard. These notes will be uploaded later.

The reading recommendations are also the same from last week, namely

Rashkca et al., chapter 11, jupyter-notebook sent separately last week, and from GitHub address https://github.com/rasbt/machine-learning-book

Goodfellow et al, chapter 6 and 7 contain most of the neural network background.

See you soon and best wishes for the week,

Keran, Morten and Ruben