Mitigating the Stability–Plasticity Trade-Off in Neural Networks via Shared Extractors in Class-Incremental Learning
Humans learn new tasks without forgetting, but neural networks suffer from catastrophic forgetting when trained sequentially. Dynamic expandable networks attempt to address this by assigning each task its own feature extractor and freezing previous ones to preserve past knowledge. While effective fo...
Na minha lista:
| Principais autores: | , , |
|---|---|
| Format: | Artigo |
| Sprog: | Inglês |
| Udgivet: |
MDPI AG
2025-10-01
|
| Serier: | Applied Sciences |
| Fag: | |
| Online adgang: | https://www.mdpi.com/2076-3417/15/19/10757 |
| Tags: |
Ingen Tags, Vær først til at tagge denne postø!
|