Weekly update and plans for week 42
Dear all, welcome back again.
Last week we discussed how to develop a feed forward neural network code. We introduced also how to set up a neural network using tensorflow and keras. Many of these topics are described extensively in the textbook by Goodfellow et al, in particular chapter 6-12. These chapters provide a good overview of the topics we cover in weeks 40-43. This week, besides the introduction to convolutional neural networks, we will also discuss how to solve differential equations using neural networks. On Thursday, we will summarize our discussions on feed forward neural networks and apply the theory to the solution of differential equations. This will be the topic for parts of Thursday's lecture. Thereafter we move on to discuss convolutional neural networks (CNNs) for the rest of this week. CNNs are well covered by Goodfellow's text chapter 9.
In summary, this week our plans are
- Lab Wednesday: Work on project 2
- Lecture Thursday: Solving differential equations with Neural Networks. Convolutional Neural Networks and classification problems
- Lecture Friday: Convolutional Neural Networks and classification problems
- Reading recommendations:
- See lecture notes for week 42 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- 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
If you wish to explore UiO's Machine Learning computers, please feel free to look up /tjenester/it/forskning/kompetansehuber/uio-ai-hub-node-project/it-resources/ml-nodes/#toc3
You can register as user and get access to high-performance computing resources for machine learning.
Give it a try!
Finally, we recommend strongly to get started with project 2!
Best wishes for the week,
Morten et al.