Interpretable AI

9 Path to explainable AI

This chapter covers

• A recap of interpretability techniques learned in this book
• Understanding the properties of an explainable AI system
• Common questions asked of an explainable AI system and applying interpretability techniques to answer them
• Using counterfactual examples to come up with contrastive explanations

We are now approaching the end of our journey through the world of interpretable AI. Figure 9.1 provides a map of this journey. Let’s take a moment to reflect on and to summarize what we have learned. Interpretability is all about understanding the cause and effect within an AI system. It is the degree to which we can consistently estimate what the underlying models in the AI system will predict given an input, ...