Plans for week 44

Dear all and welcome back to a new week!  

This week we start with convolutional neural networks. This topic continues next week with recurrent neural networks as well.

That will end our discussion of deep learning methods. The final methods we will discuss and study are decision trees, random forests, bagging and boosting methods. The latter methods will be discussed during weeks 46 and 47 (our last weeks).

This week we plan to 

Material for the active learning sessions on Tuesday and Wednesday

• Exercise on writing your own neural network code, application to the OR and XOR gates, see notes from last week. Same exercises this week
• The exercise this week is a continuation from last week
• Discussion of project 2
• Video of lab session from last week

Material for the lecture on Thursday November 2, 2023

• Convolutional Neural Networks
• Readings and Videos:
  • The lecture slides at https://compphysics.github.io/MachineLearning/doc/pub/week44/ipynb/week44.ipynb (see examples there)
  • For a more in depth discussion on neural networks we recommend Goodfellow et al chapter 9. See also chapter 11 and 12 on practicalities and applications
  • Reading suggestions for implementation of CNNs: Aurelien Geron's chapter 13

Else, we continue working on project 2 and the exercises relevant for the project. 

Best wishes to you all,

Adam, Daniel, Fahimeh, Ida, Karl Henrik, Mia and Morten

p.s. the last weekly exercise, after the deadline for project 2, is a simple one, just your feedback to the course!