| Autor: |
Murfet, Daniel, Wei, Susan, Gong, Mingming, Li, Hui, Gell-Redman, Jesse, Quella, Thomas |
| Rok vydání: |
2020 |
| Předmět: |
|
| Zdroj: |
IEEE Transactions on Neural Networks and Learning Systems 34, issue 12, pages 10473-10486, December 2023 (published online on 30 June 2022) |
| Druh dokumentu: |
Working Paper |
| DOI: |
10.1109/TNNLS.2022.3167409 |
| Popis: |
In singular models, the optimal set of parameters forms an analytic set with singularities and classical statistical inference cannot be applied to such models. This is significant for deep learning as neural networks are singular and thus "dividing" by the determinant of the Hessian or employing the Laplace approximation are not appropriate. Despite its potential for addressing fundamental issues in deep learning, singular learning theory appears to have made little inroads into the developing canon of deep learning theory. Via a mix of theory and experiment, we present an invitation to singular learning theory as a vehicle for understanding deep learning and suggest important future work to make singular learning theory directly applicable to how deep learning is performed in practice. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
