A multifidelity approach to continual learning for physical systems
We introduce a novel continual learning method based on multifidelity deep neural networks. This method learns the correlation between the output of previously trained models and the desired output of the model on the current training dataset, limiting catastrophic forgetting. On its own the multifi...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Artigo |
| Sprache: | Inglês |
| Veröffentlicht: |
IOP Publishing
2024-01-01
|
| Schriftenreihe: | Machine Learning: Science and Technology |
| Schlagworte: | |
| Online-Zugang: | https://doi.org/10.1088/2632-2153/ad45b2 |
| Tags: |
Keine Tags, Fügen Sie das erste Tag hinzu!
|