Training a physics-encoded neural network on boundary data recovers the Reissner-Nordström-AdS black hole metric, with mean squared errors ranging from 0.0015 to 0.28 across six charge and topology settings.
Reducing the dimensionality of data with neural networks.,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
hep-th 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep learning the holographic black hole with charge
Training a physics-encoded neural network on boundary data recovers the Reissner-Nordström-AdS black hole metric, with mean squared errors ranging from 0.0015 to 0.28 across six charge and topology settings.