Plans for week 43, October 24-28

Dear all, 

last week we applied neural networks to the solution of differential equations and started our discussion of convolutional neural networks. The plan this week is as follows

* Lab: Wednesday and Thursday work on project 2. The lab on Wednesdays is only at F?434.

* Lecture Thursday: Convolutional Neural Networks (CNN)

* Lecture Friday: Recurrent Neural Networks (RNN)

=== Videos and reading recommendation

Video  on Convolutional Neural Networks from MIT at https://www.youtube.com/watch?v=iaSUYvmCekI&ab_channel=AlexanderAmini

Video  on Recurrent Neural Networks from MIT at https://www.youtube.com/watch?v=SEnXr6v2ifU&ab_channel=AlexanderAmini

=== Reading Recommendations 

CNN readings

Goodfellow, Bengio, Courville, chapter 9 https://www.deeplearningbook.org/contents/convnets.html

Our discussion is tailored around the lectures from CS231 at Stanford http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture5.pdf

Michael Nielsen's book is a must read, in particular chapter 6 which deals with CNNs http://neuralnetworksanddeeplearning.com/chap6.html

RNN readings

Goodfellow et al https://www.deeplearningbook.org/contents/rnn.html, chapter 10 on Recurrent NNs, chapters 11 and 12 on various practicalities around deep learning are also recommended.

We will again borrow from the Lectures from CS231 at Stanford http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture10.pdf

Else, the lecture slides from week 43  at https://compphysics.github.io/MachineLearning/doc/pub/week43/html/week43-reveal.html with code example plus the handwritten notes would complement our material for this week.

This will conclude our deep learning discussions. If we get time, we may discuss other deep learning models.