Concept icon
Concept

When Selective Relabeling Is Acceptable

Selective relabeling can be reasonable when you only need a practical result for building a product or application. It becomes a problem when the result will be reported in a research paper or when you need an unbiased estimate of test-set performance.

0

1

Concept icon
Updated 2026-08-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy

Machine Learning Yearning @ DeepLearning.AI

Related