# On the role of neurogenesis in overcoming catastrophic forgetting

arXiv: https://arxiv.org/abs/1811.02113 · HTML: https://mlsanity.com/paper/1811.02113/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2018.

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

- [Self-Composing Policies for Scalable Continual Reinforcement Learning](https://mlsanity.com/paper/2506.14811/) (2025)
- [Lifelong Continual Learning for Anomaly Detection: New Challenges, Perspectives, and Insights](https://mlsanity.com/paper/2303.07557/) (2023)
- [Bio-Inspired, Task-Free Continual Learning through Activity Regularization](https://mlsanity.com/paper/2212.04316/) (2022)
- [TACOS: Task Agnostic Continual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2409.00021/) (2024)

## Abstract (arXiv)

Lifelong learning capabilities are crucial for artificial autonomous agents operating on real-world data, which is typically non-stationary and temporally correlated. In this work, we demonstrate that dynamically grown networks outperform static networks in incremental learning scenarios, even when bounded by the same amount of memory in both cases. Learning is unsupervised in our models, a condition that additionally makes training more challenging whilst increasing the realism of the study, since humans are able to learn without dense manual annotation. Our results on artificial neural networks reinforce that structural plasticity constitutes effective prevention against catastrophic forgetting in non-stationary environments, as well as empirically supporting the importance of neurogenesis in the mammalian brain.