Physics-constrained indirect supervised learning
ABSTRACT: This study proposes a supervised learning method that does not rely on labels. We use variables associated with the label as indirect labels, and construct an indirect physics-constrained loss based on the physical mechanism to train the model. In the training process, the model prediction...
Αποθηκεύτηκε σε:
| Κύριοι συγγραφείς: | , |
|---|---|
| Μορφή: | Artigo |
| Γλώσσα: | Inglês |
| Έκδοση: |
Elsevier
2020-03-01
|
| Σειρά: | Theoretical and Applied Mechanics Letters |
| Θέματα: | |
| Διαθέσιμο Online: | http://www.sciencedirect.com/science/article/pii/S2095034920300283 |
| Ετικέτες: |
Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!
|