6.1 Counterfactual Explanations | Interpretable Machine Learning

Machine learning algorithms usually operate as black boxes and it is unclear how they derived a certain decision. This book is a guide for practitioners to make machine learning decisions interpretable.

1 mentions: @ChristophMolnar
Date: 2020/10/23 14:22

Referring Tweets

@ChristophMolnar The counterfactual explanation chapter was improved by @SusanneDndl 🎉🎉 t.co/kQmwBufUWT Finding a counterfactual explanation means solving multiple objectives at once. There is no single best explanation, but many. See also our MOC paper: t.co/Xk1yub759c

Related Entries

Read more #70 Making Black Box Models Explainable with Christoph Molnar – Interpretable Machine Learning Resea...
0 users, 1 mentions 2019/09/25 12:50
Read more Lecture about introduction to machine learning • Introduction to Machine Learning
0 users, 1 mentions 2020/02/14 08:21
Read more PPSN 2020 – 16th International Conference on Parallel Problem Solving from Nature
0 users, 1 mentions 2020/07/13 14:21
Read more Social Sciences | Free Full-Text | Analysis of Risk Factors and Symptoms of Burnout Syndrome in Colo...
0 users, 1 mentions 2020/09/12 08:22
Read more 7.3 Detecting Concepts | Interpretable Machine Learning
0 users, 1 mentions 2021/04/07 10:48