Plans for the week of May 13-17
Dear all, this is the last week of lectures and due to a Machine Learning workshop starting Tuesday (see https://sites.google.com/view/physmlworkshop24/program if you are interested) we decided to move Tuesday's lecture to Monday at 1015am-12pm.
Same place as before and for those who cannot attend in person, zoom is an option. And the last session will also be recorded.
We will also have lab on Thursday and throughout May for those interested. We will keep our labs at Thursdays.
On Monday the plan is to give a summary of what we have covered this semester. This year we have covered
We have covered
- Discriminative methods
a. With a review of neural networks
b. CNNs and RNNs
c. Autoencoders and Principal component analysis
2. Generative methods
a. Energy-based models
b. Variational autoencoders
c. Diffusion based models
d. Generative adversarial networks
We will try to summarize what we have done, with pros and cons and more. Feel also free to come with feedback to us. We will send out a feedback form later. Since this course has been defined as a self-study course, there are clearly limitations to what can be covered and our focus has been on deep learning methods, with an almost equal emphasis on discriminative and generative models. Your thoughts about the lecture content is thus most welcome.
The summary slides (more material will be added through the weekend) are at for example https://github.com/CompPhysics/AdvancedMachineLearning/blob/main/doc/pub/week17/ipynb/week17.ipynb
Best wishes to you all,
Keran, Morten and Ruben