Plans for the week Feb 12-16

Dear all and welcome back to a new week with FYS5429. Before we outline the plans for tomorrow's lecture (Tuesday Feb 13), we would like to 

1) remind you that tomorrow's lecture is digital only via zoom, our zoom link is

FYS5429 zoom link https://msu.zoom.us/j/6424997467?pwd=TEhTL0lmTmpGbHlnejZQa1pCdzRKdz09Links to an external site.

Meeting ID: 642 499 7467 Passcode: FYS4411

2) we have found time and an available room for our lab sessions!  From this coming Thursday at 2pm-4pm, we have room FØ397 available for us. Keran and Ruben will be there.  This course being listed as a self-study course was originally not planned to have a lab but seen all the enlisted participant, we have decided to offer a time slot dedicated for lab activities. 

The plans for this week are to discuss the basics of convolutional neural networks and how to develop your own code.

We are aiming at the following 

Plans for February 12-16

• Basics and mathematics of Convolutional Neural Networks.

• Reading recommendations:

a. For neural networks we recommend Goodfellow et al chapters 6 and 7. For CNNs, see Goodfellow et al chapter 9. See also chapter 11 and 12 on practicalities and applications

b. Reading suggestions for implementation of CNNs: Rashcka et al.'s chapter 14Links to an external site.. The jupyter-notebook for this chapter is available from Rachska's GitHub site. It is also sent separately to you all.  The lecture notes for this week are at  https://github.com/CompPhysics/AdvancedMachineLearning/blob/main/doc/pub/week5/ipynb/week5.ipynbLinks to an external site.

Some updates (typos and some additional material will be added during the day today).

Note also that we have separated out the code for neural networks from last week, including some additional comments we did not discuss. 

We will start the lecture tomorrow with a reminder from that part, since the basic code structure is used in the CNN code as well.

This material is at https://github.com/CompPhysics/AdvancedMachineLearning/blob/main/doc/pub/NNpart5code/ipynb/NNpart5code.ipynbLinks to an external site.

It is a generalization of what we discussed last week.

Finally, for those interested in PINNs, Adam Jacobsen has developed a very nice framework for solving the diffusion equation. Adam is working on this topic for his Master thesis and the PyTorch environment could be of interest to many of you. Feel free to take a look at  https://github.com/CompPhysics/AdvancedMachineLearning/blob/main/doc/Programs/DiffusionPINNs/diffusion_pytorch.ipynbLinks to an external site.

Best wishes to you all,

Keran, Morten and Ruben