# Explaining How Deep Neural Networks Forget by Deep Visualization

arXiv: https://arxiv.org/abs/2005.01004 · HTML: https://mlsanity.com/paper/2005.01004/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2020.

## Built on by (most cited first, 4 of 4)

- [The effectiveness of feature attribution methods and its correlation with automatic evaluation scores](https://mlsanity.com/paper/2105.14944/) (2021)
- [Interpretable LLM-based Table Question Answering](https://mlsanity.com/paper/2412.12386/) (2024)
- [Overcoming Catastrophic Forgetting by XAI](https://mlsanity.com/paper/2211.14177/) (2022)
- [Semi-supervised Neural Machine Translation with Consistency Regularization for Low-Resource Languages](https://mlsanity.com/paper/2304.00557/) (2023)

## Abstract (arXiv)

Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life. Taking the advantages of interpretable machine learning (interpretable ML), this paper proposes a novel tool called Catastrophic Forgetting Dissector (or CFD) to explain catastrophic forgetting in continual learning settings. We also introduce a new method called Critical Freezing based on the observations of our tool. Experiments on ResNet articulate how catastrophic forgetting happens, particularly showing which components of this famous network are forgetting. Our new continual learning algorithm defeats various recent techniques by a significant margin, proving the capability of the investigation. Critical freezing not only attacks catastrophic forgetting but also exposes explainability.