635: The Perils of Manually Labeling Data for Machine Learning Models
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Is There a Bias Parameter?
Bias is just an act of shifting the effective model to one side or another. The way supervised machine learning has evolved over time has made it very reliant on hand labeled data, which is where bias can creep in. These days, most of the time, your models not biased because you trained an inherently biased like architecture. It's usually because your data is biased in some way, you know, degeneratively biased.
Transcript
Play full episode
