Plans for week 45

Dear all, we hope the weekend has elapsed in the best possible way for you all. Last week we were unfortunate since our lecture hall was reserved for high school teachers (annual event across the university). We ended thus up with project work only and had to defer the lecture on convolutional neural networks to a recording only. I am however not happy with the recording I made this weekend and will thus make a new one on convolutional neural networks (CNNs). Hopefully it will be done by the end of Monday November 6.

However, till then you can watch the recordings on CNNs from last year at https://youtu.be/MdYT6uwOkT0 (second lecture) and https://youtu.be/3bDkrB-E7cU.

This week we end our discussions on deep learning methods by presenting another method, namely recurrent neural networks. We will also summarize our discussions on deep learning and project 2. Next week (week 46)  and for our last week (week 47) we will discuss our last set of methods for this semester, so-called decision trees, random forests and other aggregation methods. 

The material for the lab sessions this week contains a discussion of other ways to classify results from a classification study (confusion matrix and more) as well as ways to perform a grid search for finding optimal parameters.  We will obviously also continue with our work on project 2.

You will find all this in the weekly slides for this week, see for example the jupyter-notebook at https://compphysics.github.io/MachineLearning/doc/pub/week45/ipynb/week45.ipynb

Best wishes to you all,

Morten et al