Screening for Failures You Haven’t Seen Yet
Supervised machine learning asks: does this unit resemble a defect we've seen before?
Useful takeaways from this story.
Supervised machine learning asks: does this unit resemble a defect we've seen before?
Conventional screening asks: does this unit violate a limit we set?
Both questions require us to already know what we're hunting.
Building the complete brief
The page is ready to read now. The fuller skim-friendly version will appear here automatically.
The useful part
Supervised machine learning asks: does this unit resemble a defect we've seen before? Conventional screening asks: does this unit violate a limit we set? Both questions require us to already know what we're hunting.
Details worth keeping
Conventional screening asks: does this unit violate a limit we set? Both questions require us to already know what we're hunting.
Keep reading in the app
Open the app view to save this story, compare related coverage, and continue from the same source.