What is Concept Drift and How to Solve It
Introduction
Reposted with permission from Devansh. Thanks to their versatility, Neural Networks are a staple in most modern Machine Learning pipelines. Their ability to work with unstructured data is a blessing since it allows us to partially — partially being important here — replace domain insight (expensive and hard to attain) with computational scale (cheaper and easier to attain). However, turns out that blindly stacking layers and throwing money at problems doesn't work as well as some people would like you to believe. There are several underlying issues with the training process that scale does not fix, chief amongst them being distribution shift and generalization.