Get a head start on AI/ML transparency with explorable explanations

The system can convey why. Interpretable: The user can determine how. Transparent: The provenance of the result can be traced all the way back to the training data. These features are not widespread within commercial AI/ML contexts. This means there's an opportunity: not only to differentiate, but also to de-risk the use of AI/ML systems in business. Every AI/ML system that could have regulatory, legal, consumer, or academic contact, may one day be required to explain how it makes decisions. We can build expertise in explaining systems — and trust with designers, developers, and end-users — by starting with explaining non-AI/ML systems.