Unlock the Blackbox - Demystifying Machine Learning Explainability!
Machine learning (ML) has great potential for improving processes and products. A challenge is to explain the predictions of the ML algorithms. Trust and transparency are central arguments for the explainability of decision findings by an ML model.
In this article, we introduce the basic concepts of Explainable Artificial Intelligence (XAI). Furthermore, we present the properties or requirements of an explanation. In the context of this article, we use the terms interpretable and explainable synonymously.
We’ll discuss the following points:
- Taxonomy of Explainable Machine Learning
- Goals of explainability
- Properties of explanations
- Results of explanation methods
- Conclusion
The complete article is available in our members' area. As a member, you get access to super-detailed articles about data science and software engineering topics.
