Plans for week 45, November 4-8

Plans for week 45, November 4-8

Dear all, we hope all is going well with the finalization of project 2. Keep in mind that you always have one extra day to mend/correct/improve your submission. But do please uplaod your GitHub/Gitlab or similar links or files by the deadline Monday at midnight.

This coming we will start discussing project 3. The project will be available from Monday evening (November 4).

Note also that the lecture this Monday (November 4) is via zoom only, no in person lecture.  As always, the lecture will be recorded.

Plans for week 45

Material for the lecture on Monday November 4, 2024.

1. Convolutional Neural Networks, codes and examples (own code and TensorFlow and Pytorch implementations)

2. Recurrent Neural Networks (RNNs)

3. Readings and Videos:

a. These lecture notes at https://github.com/CompPhysics/MachineLearning/blob/master/doc/pub/week45/ipynb/week45.ipynbLinks to an external site.

b. For a more in depth discussion on CNNs and recurrent neural networks we recommend Goodfellow et al chapters 9 and 10. See also chapter 11 and 12 on practicalities and applications

c. Reading suggestions for implementation of CNNs and RNNs, see Raschka et al chapters 14-15 at https://github.com/rasbt/machine-learning-bookLinks to an external site..

d. Video on Recurrent Neural Networks from MIT at https://www.youtube.com/watch?v=SEnXr6v2ifU&ab_channel=AlexanderAminiLinks to an external site.

e. Video on Deep Learning at https://www.youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3piLinks to an external site.

Material for the lab sessions, additional ways to present classification results and other practicalities

Material for the active learning sessions on Tuesday and Wednesday.

1. Discussion of and work on project 3, available from Monday November 4, late evening

Best wishes to you all with the finalization of project 2.

Fahimeh, Ida, Karl Henrik, Mia, Morten, Odin and Sigurd.

p.s. Note that there was an error in the weekly exercises for week 42. The cross entropy was wrongly defined there, see https://scikit-learn.org/stable/modules/generated/sklearn.metrics.log_loss.html for the correct expression.Links to an external site.

We apologize for this and hope it has not caused any problems.