Invitation - Short Course Machine Learning

[Madlene Nussbaum]

<English below>


Liebe R User

Am letzten Treffen haben wir R und Datenbanken besprochen. Die Unterlagen sind hier auf
dem Git-Repo:
http://git.bfh.ch/gitweb/?p=staff/nam1/teach/BFH-R-User-Group.git;a=tree;f=3_past-meetings-docs/20200211_database-postgreSQL


Weiter haben wir die Wünsche der BFH R User zusammengetragen und priorisiert. Weit oben
lag mein Machine-Learning-Kurs, zu welchem ich bereits Unterlagen habe. Ich schlage einen
ganzen Kurs-Tag vor, damit wir mit dem Inhalt durchkommen und die Übungen vor Ort gemacht
werden können. Programm siehe unten.
Interessiert? Bitte in Doodle eintragen bis 29.2.2020:

https://doodle.com/poll/ubaq656fkx7769kn

Liebe Grüsse Madlene


---
Dear R Users

At the last meeting we discussed R and databases. Please find the documents on the Git
repository:
http://git.bfh.ch/gitweb/?p=staff/nam1/teach/BFH-R-User-Group.git;a=tree;f=3_past-meetings-docs/20200211_database-postgreSQL

Moreover, we collected and prioritized the needs of the BFH R users. My machine learning
course was often selected. I have presentations and exercises ready on this topic, hence,
I propose a full day course to be able to treat all the topics and support you during the
exercises. See below for the program.
Interested? Please fill in the Doodle until 29.2.2020.
https://doodle.com/poll/ubaq656fkx7769kn

All the best,
Madlene



======= Program =======

**Short Course: Mastering Machine Learning for Prediction**

Time: 10:30 - 17:00 Location: presumably HAFL, Zollikofen

Language lecture: English if requested, else German.
Language materials: English.

Expected previous knowledge: Basic know-how of simple and multiple linear regression
(ordinary least squares-method).
e.g. catch up by watching these very simple explanatory videos (1 hour on speed 1.25):
https://www.youtube.com/watch?v=Qa2APhWjQPc
https://www.youtube.com/watch?v=iAgYLRy7e20
https://www.youtube.com/watch?v=dQNpSa-bq4M

Please feel free to just join for a part of the course.

Suggested Schedule
------------------------------

Morning: Repeat linear regression if needed (self-study)

10:30 Part I: Introduction and Overview of Machine Learning Methods for Prediction,
Overfitting. Methods in the Context of Supervised Learning: Lasso, Support Vector
Machines, Random Forest, Boosting, Model averaging.

12:00 Lunch Break (Mensa)

13:00 Practical training, Exercises Part I

14:00 Part II: Model Selection and Model Building, Model Interpretation, Prediction
Intervals, Uncertainty, parametric and non-parametric Bootstrap

15:00 Coffee Break

15:20 Practical training, Exercises Part II

16:20 Part III: Model Evaluation, Cross-Validation, Validation Statistics, Good Practice
and Interpretation, R2 vs. r2, Scores for Classification.
-----