Summary

Interpretable machine learning is an extensive topic, and this book has only covered some aspects of some of its most important areas on two levels: diagnosis and treatment. Practitioners can leverage the tools offered by the toolkit anywhere in the ML pipeline. However, it’s up to the practitioner to choose when and how to apply them.

What matters most is to engage with the tools. Not using the interpretable machine learning toolkit is like flying a plane with very few instruments or none at all. Much like flying a plane operates under different weather conditions, machine learning models operate under different data conditions, and to be a skilled pilot or machine learning engineer, we can’t be overconfident and validate or rule out hypotheses with our instruments. And much like aviation took a few decades to become the safest mode of transportation, it will take AI a few decades to become the safest mode of decision-making. It will take a global village...