AI Foundations
Underfitting
When a model is too simple or insufficiently trained to capture important patterns.
Example
A model is too simple to capture the relationship between weather and electricity demand.
Why it matters
The term helps teams recognize when their chosen approach is missing patterns they need.
You'll hear it
“It isn't doing well even on the examples it practiced.”
Can you control it?
Not directly
No direct control. This describes a wider issue, concept or result rather than something you can simply switch on or off in a tool.
Common questions
- How can I tell if a model is underfitting?
- It performs poorly on both training data and new evaluation data.
- Will simply adding more examples always solve it?
- No. An approach that is too limited may still be unable to learn the needed pattern.
- Is underfitting the opposite of overfitting?
- They are different failures: one misses useful patterns, while the other learns practice details too closely.