How Models Learn

Underfitting

When a model is too simple to capture the pattern, so it does poorly even on its training data.

On the left of the U, the model is underfitting: too simple to capture the pattern — a straight line can’t do summer and winter — so it does badly on training and test days alike.
From Overfitting, step “Too simple, too flexible, just right”

See it in action

Try underfitting hands-on in the lesson Overfitting, part of the AI fundamentals course.

Open the lesson