We had hubris a couple years ago, thinking you could create accurate machine learning (ML) models completely unsupervised. Turns out, we do need some human supervision—just enough human knowledge to train the model properly.

Building machine learning models can be exhilarating, but the process to get to the final model can often be tedious. Inexperienced data science teams may encounter hidden obstacles they either can't handle or don't know about.

Confusion matrices are the tried-and-true way to evaluate the metrics for machine learning classifiers. Is updating them really so confusing?

Long story short, humans are slow, taking at least 10 seconds to label one example. However, a machine can make the same judgement in milliseconds.

The history of using machines to understand the meaning of natural language started as early as World War II and continues through present day.

Until recently, natural language processing (NLP) applications have been limited in their ability to understand nuance and context. What's changed?