Human-in-the-loop Machine Learning

Motivation

The goal of a Human-In-The-Loop Machine Learning framework is to go from 0 labeled data to accurately labeled data in as little time, and with as little effort, as possible. This framework is most applicable to supervised classification tasks.

Towards this end, there are 3 critical components:

• The data, cleaned and ready for training
• The interface, optimized for efficient labeling
• The model, which will be iteratively trained and used for data screening