thomaskeck.github.io

Machine Learning Lectures

This repository contains an updated version of my lectures and workshops given at:

• The CERN Computing School in Mol 2016 and in Madrid 2017
• The GRIDKA School in Karlsruhe 2017
• The KSETA Topical Courses in Karlsruhe 2017
• The Machine learning workshop in Paris 2018

The talks are javascript and html-based using reveal.js and d3.js. They can be viewed online via github pages:

• On Traditional Machine Learning
• On Deep Learning
• On Machine Learning at KIT and Belle II

The workshops are provided as jupyter notebooks, which can be served as reveal.js presentations.

Howto clone this repository

This repository uses git submodules:

git clone –recurse-submodules https://github.com/thomaskeck/thomaskeck.github.io

Howto print the slides

There are two options to convert the html-based presentation into a printable pdf file

• Chrome: In chrome you can append ?print-pdf to the URL of the talk and print the website into a pdf. Check the preview in chrome in order to ensure that the output looks reasonable.
• Decktape: with decktape you can render the html slides and take screenshots, this has the advantage that it works with the animations

I usually do something like this: First I serve the slides on a local web-server using python

python3 -m http.server

Afterwards I use decktape via docker to create screenshots of each rendered page with a large pause in between the screenshots to ensure that the animations finish.

docker run –shm-size 2G –rm -t –net=host -v pwd:/slides astefanutti/decktape generic –key=n –screenshots -p 15000 -s ‘1240x874’ –max-slides 150 http://localhost:8000/talks/MachineLearning.html temp.pdf

Finally I remove all uninteresting slides by hand to create a clean version of the pdf.

convert $(ls -v screenshots/*.png) machine_learning.pdf

Deprecated Repositories

The original repositories with the previous content and exercises are available here:

• CSC Lecture
• GridKA School

Further Reading

An (incomplete) list of interesting books:

• Christopher M. Bishop. Pattern Recognition and Machine Learning
• Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning.
• J. Han, M. Kamber, J. Pei. Data Mining: Concepts and Techniques
• O. Behnke, K. Kröninger, G. Scott, T. Schörner-Sadenius. Data Analysis in High Energy Physics: A Practical Guide to Statistical Methods
• I. Goodfellow, Y. Bengio, A. Courville. Deep Learning (Adaptive Computation and Machine Learning)
• R. S. Sutton, and A. G. Barto. Reinforcement Learning: An Introduction

You can find a list of research publications I enjoyed reading here