Concept icon
Concept

A Big Gap Between Training and Development Error Suggests Overfitting

In a document-classification task, suppose a model gets 3% error on the training set but 14% error on the development set. That pattern indicates high variance: the model fits the training data well but does not generalize well to new examples. This kind of generalization failure is also called overfitting.

0

1

Concept icon
Updated 2026-08-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Machine Learning Strategy

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Yearning @ DeepLearning.AI

Related