Books

Maschinelles Lernen – Grundlagen und Algorithmen in Python

Below is a link to a ZIP archive containing all source code from the book along with some prepared data sources. The listings are tested for the Python library versions listed below.

Since 2019/20 the continuing education project WeAI at Bochum University of Applied Sciences has been based on this book. There is also a YouTube lecture series that can serve as a supplement to online teaching. In my experience, reading and hands-on practice always works better, though.

Software requirements: Python 3.7.6, NumPy 1.18.5, SciPy 1.5.0, Matplotlib 3.2.2, Pandas 1.0.5, TensorFlow/Keras 2.1.0, GeoPandas 0.6.1, scikit-learn 0.22.1, OpenAI Gym 0.17.2

Finite-Elemente-Methode – Eine praxisbezogene Einführung mit GNU Octave/MATLAB

Erratum: hints on further errors are welcome by e-mail. Some code is continuously improved within the FFEP project.

Software requirements: GNU Octave 4.0.0 (or MATLAB), Gmsh 2.10.1

Maschinelles Lernen – Grundlagen und Algorithmen in Python (1st & 2nd edition)

The publisher released the book in 2018 (green cover) and reprinted it in 2019 (red cover). Both editions have the same content, except that the 2019 reprint corrects several errors. An erratum was maintained for both until mid-2020 and is available below. The source code is identical for both editions and is no longer actively maintained.

Software requirements: Python 3.6.3, NumPy 1.12.1, SciPy 1.0.0, Matplotlib 2.1.0, scikit-learn 0.19.1 (Kapitel 10), Keras 2.0.8 (Kapitel 8 und 12)