Trustworthy Machine Learning
This book is used as a coursebook at the University of Tübingen.
Authors
Broad use of machine learning is not just a matter of whether it works or not – even if it works very well, it is difficult to trust these models.
When our life, health, or money is at stake, society is naturally cautious with machine learning.
With the sudden spark of generative artificial intelligence, people might also find it hard to gain trust for the generated content.
This book aims to uncover how we can increase the trustworthiness of our machine learning models.
Topics of the book
01
Out-Of-Distribution Generalization
02
Explainability
03
Uncertainty
04