---
title: "Catastrophic forgetting"
description: "The tendency of neural networks to lose earlier competence when trained on new tasks."
canonical: https://aigovernanceengineer.com/glossary/catastrophic-forgetting
author: "Jorge García Aibar"
license: "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)"
doi: https://doi.org/10.5281/zenodo.22956197
version: "0.5.0"
updated: 2026-09-24
---

# Catastrophic forgetting

The tendency of neural networks to lose earlier competence when trained on new tasks [1]. It is a reason every retraining is a change event that re-runs the full eval suite, not only the tests for the new capability.

- Developed in: [ch. 11, Eight characteristics that break classic IT governance](https://aigovernanceengineer.com/bok/ai-defined#eight-characteristics-that-break-classic-it-governance)
- Chapters: [ch. 11, AI Defined](https://aigovernanceengineer.com/bok/ai-defined)
- In the glossary chapter: https://aigovernanceengineer.com/bok/glossary#t-catastrophic-forgetting

## Sources

[1] Overcoming catastrophic forgetting in neural networks (networks lose earlier competence when trained on new tasks; arXiv 1612.00796). Kirkpatrick et al.. 2016-12-02. https://arxiv.org/abs/1612.00796 (verified: primary)