Introduction to Local Interpretable Model-Agnostic Explanations (LIME) by Marco Tulio Ribeiro, Sameer Singh and Carlos Guestrin via @OReillyMedia

Local interpretable model-agnostic explanations (LIME) is a technique to explain the predictions of any machine learning classifier. Here's an introduction to LIME and how it works.

I found this really interesting. I guess this is a similar to SMART for objectives.