Chapter 10 Acknowledgements
Writing this book was (and still is) a lot of fun. But it’s also a lot of work and I am very happy about the support I received:
A special thanks goes to Verena Haunschmid for contributing the section about LIME explanations for images. She works in data science and I recommend following her on Twitter: @ExpectAPatronum. I also want to thank all the early readers who contributed smaller fixes on github!
Further, I want to thank everyone involved in creating illustrations: The cover was designed by my friend @ArbeitAmText. The graphics in the Shapley Value chapter were made by Abi Aryan, using icons made by Freepik from Flaticon. The awesome images in the chapter about the future of interpretability are designed by @TopeconHeroes. Verena Haunschmid created the graphic in the RuleFit chapter. I often used images from the papers directly. I would like to thank all researchers who allowed me to use images from their publications.
In at least three aspects, the way I publish the book is unconventional. First, it’s available both as a website and as an ebook/pdf. The software I used to build this book is called
bookdown, written by Yihui Xie, who created many R packages that make it so easy to combine R code and text. Thanks a lot! Secondly, I self-publish the book on the platform Leanpub, instead of working with a traditional publisher. And third, I have published the book as in-progress book, which has helped me enormously to get feedback and to monetize it along the way. Many thanks to leanpub for making this possible and handling the fees fairly. I would also like to thank you, dear reader, for reading this book without having a big publisher name behind it.
I am grateful for the funding of my research on interpretable machine learning by the Bavarian State Ministry of Science and the Arts in the framework of the Centre Digitisation.Bavaria (ZD.B).