Weekly plans for FYS-STK3155/4155

Dear All,

here comes the weekly update with plans etc. 

Last week we finalized neural part for now, ending with a more superficial discussion of Convolutional NNs. This is an important field, in particular in imaging. For those of you interested, there is a dedicated course (spring, IN5400) on imaging and machine learning taught by Anne Solberg. It is highly recommended. We limited ourselves to an overarching view and ow to use 

CNNs with tensorflow and keras. 

This week we will discuss other methods for classification in particular, but we will also discuss some famous methods for dimensionality reduction. The plan for the rest of the semester looks like as follows

1) This week (week 43):

     Thursday: Dimensionality reduction, principal component analysis and other methods, see the text of      Geron chapter 8 or chapter 3 of hastie et al. Chapter 12 of Murphy gives an excellent math introduction.

      Friday: Start discussing support vector machines (SVM), see chapter 12 of Hastie et al and chapter 5 of Geron.

2) Next week (week 44):

    Thursday and Friday: end discussion of SVM and start discussing random forests/trees and nearest neighbors, see chapter 6 of Geron and chapter 9 of Hastie.

3) Week  45: unsupervised learning, Boltzmann machines mainly, and including Gibbs and Metropolis sampling.     Own notes

4) Weeks 46 and 47: Bayesian statistic, own notes

5) Last week of the semester, week 48: Last lecture November 29.

And then the final workshop with poster presentations of project 3 on November 30. Please let me know if this fits your plans.

Also, feel free to suggest data to analyze for project 3. In project 3 you can reuse all methods you have developed you have developed for projects 1 and 2 or use scikit-learn/tensorflow/keras. But you will have to add an additional method like SVM, forest families or nearest neighbors.

At the lab we continue with project 2. 

Best wishes to you all,

Morten