Which term measures error from a model's assumptions, even with infinite training data?
Bias, the error built into the kind of model chosen.
- Bias ✔
- Variance
- Irreducible noise
Why: Bias comes from a model's built-in assumptions, like forcing a straight line. Even infinite training data cannot remove that model error. Variance instead measures how much the fitted model changes across training sets.
Huh, didn't know that: Expected test error splits into three parts: variance, bias squared and noise in the data itself.
My model has a bias for straight lines. I told it life has curves.
References
Answer: Bias. Bias comes from a model's built-in assumptions, like forcing a straight line. Even infinite training data cannot remove that model error. Variance instead measures how much the fitted model changes across training sets.
- Cornell CS4780 Lecture 12: Bias-Variance Tradeoff www.cs.cornell.edu/courses/cs4780/2018fa/lectures/lecturenote12.html
What is the inherent error that you obtain from your classifier even with infinite training data?
Checked 2026-10-10.
Think this answer is wrong? Tap "Challenge this answer" on the card in the game and tell us why.
More stuff everyone should know
That's stuff everyone should know.