Plans for week 42, October 13-17

Dear all, welcome back to a new week and new exciting possibilities! We trust you had a restful and enjoyable weekend.

This week, both for the lectures and the lab sessions, the aim is to continue our discussions on how to build a feed forward neural network code (FFNN).

Neural networks are the basic building stone of almost all advanced deep learning methods, from the standard FFNN, via convolutional neural networks to generative methods and reinforcement learning as well. Mastering the basic building blocks is thus central to our understanding of most of the deep learning methods. Deep learning methods are the focus of the rest of the semester. 

This week our focus is on 

Lecture October 13, 2025

1. Building our own Feed-forward Neural Network and discussion of project 2

2. Project 2 is available at https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/2025/Project2/ipynb/Project2.ipynb

Readings and videos

1. The lecture notes for this week and last week, see attachment.

2. For a more in depth discussion on neural networks we recommend Goodfellow et al chapters 6 and 7. For the optimization part, see chapter 8.

3. Neural Networks demystified at https://www.youtube.com/watch?v=bxe2T-V8XRs&list=PLiaHhY2iBX9hdHaRr6b7XevZtgZRa1PoU&ab_channel=WelchLabs

4. Building Neural Networks from scratch at https://www.youtube.com/watch?v=Wo5dMEP_BbI&list=PLQVvvaa0QuDcjD5BAw2DxE6OF2tius3V3&ab_channel=sentdex

5. Video on Neural Networks at https://www.youtube.com/watch?v=CqOfi41LfDw

6. Video on the back propagation algorithm at https://www.youtube.com/watch?v=Ilg3gGewQ5U

Material for the lab sessions on Tuesday and Wednesday

1. Exercises on writing a code for neural networks, back propagation part, see exercises for week 42 at https://compphysics.github.io/MachineLearning/doc/LectureNotes/_build/html/exercisesweek42.html

2. Discussion of project 2

So, today, we will discuss in more detail how to write our own codes for neural networks. 

And we will practice this in the lab sessions. The exercise set this week, together with the one from last week, should contain the essential elements in setting up your own neural network code.

Best wishes to you all,

Morten et al

p.s. Note: we may revise (typos and minor things) the text of project 2 during the Monday October 13, The final version is the one that is available from midnight on October 13.