Unified regularity measures for sample-wise learning and generalization
Abstract Fundamental machine learning theory shows that different samples contribute unequally to both the learning and testing processes. Recent studies on deep neural networks (DNNs) suggest that such sample differences are rooted in the distribution of intrinsic pattern information, namely sample...
Shranjeno v:
| Principais autores: | , , , , , , , |
|---|---|
| Format: | Artigo |
| Jezik: | Inglês |
| Izdano: |
Springer
2024-12-01
|
| Serija: | Visual Intelligence |
| Teme: | |
| Online dostop: | https://doi.org/10.1007/s44267-024-00069-4 |
| Oznake: |
Brez oznak, prvi označite!
|