Machine-learning the string landscape
We propose a paradigm to apply machine learning various databases which have emerged in the study of the string landscape. In particular, we establish neural networks as both classifiers and predictors and train them with a host of available data ranging from Calabi–Yau manifolds and vector bundles,...
Saved in:
| Published in | Physics letters. B Vol. 774; no. C; pp. 564 - 568 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
10.11.2017
Elsevier |
| Online Access | Get full text |
| ISSN | 0370-2693 1873-2445 |
| DOI | 10.1016/j.physletb.2017.10.024 |
Cover
| Summary: | We propose a paradigm to apply machine learning various databases which have emerged in the study of the string landscape. In particular, we establish neural networks as both classifiers and predictors and train them with a host of available data ranging from Calabi–Yau manifolds and vector bundles, to quiver representations for gauge theories, using a novel framework of recasting geometrical and physical data as pixelated images. We find that even a relatively simple neural network can learn many significant quantities to astounding accuracy in a matter of minutes and can also predict hithertofore unencountered results, whereby rendering the paradigm a valuable tool in physics as well as pure mathematics. |
|---|---|
| ISSN: | 0370-2693 1873-2445 |
| DOI: | 10.1016/j.physletb.2017.10.024 |