Snorkel is a fundamentally new interface to ML without hand-labeled training data

The directness of rules with the flexibility of ML. Rule-based systems have long been used in industry for certain tasks—as an input, individual rules have the desirable property of being direct and interpretable. However, rules can also be brittle, and lack the robustness, flexibility, and sheer power of ML approaches. With Snorkel Flow, you get the best of both worlds: rules (and other interpretable resources) as inputs, and powerful ML models that generalize beyond these rules as the output.

This is a very interesting project out of Stanford AI labs. I was involved in building rules engine systems in the early 2000's and know both how powerful and brittle they can be. The idea that you could start with a rules engine and then feed that into a neural net seems like both a) a good idea, and b) a good descriptor for how our own brains work.

Follow this.


Want to receive more content like this in your inbox?