Plans for week 42, October 17-21

Dear all, last week we discussed how to build a neural network. The topics covered last week, with pertinent videos (videos should be available now, I was not too happy with the first iterations) were

- Lecture Thursday: Deep learning and Neural Networks, developing a code for Neural Networks, discussion of the back propagation algorithm

  - Video of Lecture at https://youtu.be/yzbxJI6LgL0

- Lecture Friday: Building a neural network

  - Video of Lecture at https://youtu.be/CPj4mh7M9no

This week we will focus on further discussions of neural networks, their pros and cons, how to use TensorFlow and Keras, more examples and applications to the solution of differential equations and if we get time, we will start discussing convolutional neural networks. 

This week looks thus like this:

-Wednesday and Thursday Lab: work on project 2

-Thursday lecture Solving differential equations with Neural Networks and intro to Tensorflow with  examples. Discussion of project 2

-Friday lecture: More on neural networks and start Convolutional  Neural Networks.

* Reading recommendations:

  o See lecture notes for week 42 at https://compphysics.github.io/MachineLearning/doc/web/course.html.

  o For Tensorflow and Keras, see lecture notes from week 41

  o 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

  o Reading suggestions for implementation of CNNs: Aurelien Geron's chapter 13 at https://github.com/CompPhysics/MachineLearning/blob/master/doc/Textbooks/TensorflowML.pdf

Best wishes to you all,

Morten et al