Cascade Design Pattern

Waterfall pipeline of Models

Keyed Predictions

Scaling your ML service to millions of inputs.

Two-Phase Predictions—Hybrid mode of model deployment

Did you ever try to figure out how Alexa, Google Assistant, or any always-listening digital voice assistant devices are able to respond to every query of the user, without featuring complex AI hardware? We already know because of the device constraints, models deployed on edge devices need to balance the

Ensemble—A Bundle of ML Models

It becomes harder to beat a group of weak warriors.

Random splitting is Wicked.

Learn how to perform Repeatable Splitting