Black Holes and the loss landscape in machine learning
Abstract Understanding the loss landscape is an important problem in machine learning. One key feature of the loss function, common to many neural network architectures, is the presence of exponentially many low lying local minima. Physical systems with similar energy landscapes may provide useful i...
| Published in: | Journal of High Energy Physics |
|---|---|
| Main Authors: | , , |
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-10-01
|
| Subjects: | |
| Online Access: | https://doi.org/10.1007/JHEP10(2023)107 |