이상치

Values distant from most other values.

Machine learning

In machine learning, any of the following are outliers:1

  • Input data whose values are more than roughly 3 standard deviations from the mean.
  • weights with high absolute values.
  • Predicted values relatively far away from the actual values.

Outliers are often caused by typos or other input mistakes. In other cases, outliers aren’t mistakes; after all, values five standard deviations away from the mean are rare but hardly impossible.1

Outliers often cause problems in model training. Clipping is one way of managing outliers.1

Footnotes

  1. developers.google.com/machine-learning/glossary#outliers 2 3

2024 © ak