# Localizing Catastrophic Forgetting in Neural Networks

arXiv: https://arxiv.org/abs/1906.02568 · HTML: https://mlsanity.com/paper/1906.02568/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2019.

## Built on by (most cited first, 7 of 7)

- [Elastic Weight Consolidation (EWC): Nuts and Bolts](https://mlsanity.com/paper/2105.04093/) (2021)
- [A Parameter-free Adaptive Resonance Theory-based Topological Clustering Algorithm Capable of Continual Learning](https://mlsanity.com/paper/2305.01507/) (2023)
- [Privacy-preserving Continual Federated Clustering via Adaptive Resonance Theory](https://mlsanity.com/paper/2309.03487/) (2023)
- [An Adaptive Resonance Theory-based Topological Clustering Algorithm with a Self-Adjusting Vigilance Parameter](https://mlsanity.com/paper/2511.17983/) (2025)
- [Class-wise Classifier Design Capable of Continual Learning using Adaptive Resonance Theory-based Topological Clustering](https://mlsanity.com/paper/2203.09879/) (2022)
- [Technical Report for the 5th CLVision Challenge at CVPR: Addressing the Class-Incremental with Repetition using Unlabeled Data -- 4th Place Solution](https://mlsanity.com/paper/2503.15697/) (2025)
- [Diagnosing Representation Dynamics in NER Model Extension](https://mlsanity.com/paper/2510.17930/) (2025)

## Abstract (arXiv)

Artificial neural networks (ANNs) suffer from catastrophic forgetting when trained on a sequence of tasks. While this phenomenon was studied in the past, there is only very limited recent research on this phenomenon. We propose a method for determining the contribution of individual parameters in an ANN to catastrophic forgetting. The method is used to analyze an ANNs response to three different continual learning scenarios.