Deep learning the holographic black hole with charge

DOI10.1142/S0218271819501530zbMATH Open1432.83010arXiv1908.01470OpenAlexW3102158583WikidataQ127434423 ScholiaQ127434423MaRDI QIDQ5221253FDOQ5221253

Authors: Jing Tan, Chong-Bin Chen 

Publication date: 25 March 2020

Published in: International Journal of Modern Physics D (Search for Journal in Brave)

Abstract: We use the deep learning algorithm to learn the Reissner-Nordstr"om(RN) black hole metric by building a deep neural network. Plenty of data is made in boundary of AdS and we propagate it to the black hole horizon through AdS metric and equation of motion(e.o.m). We label this data according to the values near the horizon, and together with initial data constitute a data set. Then we construct corresponding deep neural network and train it with the data set to obtain the Reissner-Nordstrom(RN) black hole metric. Finally, we discuss the effects of learning rate, batch-size and initialization on the training process.

Full work available at URL: https://arxiv.org/abs/1908.01470

Recommendations

• Holography as deep learning
• Neural network approximations for Calabi-Yau metrics
• Deep learning approach to Hubble parameter
• Deep learning in the heterotic orbifold landscape
• Learning algebraic models of quantum entanglement

zbMATH Keywords

deep learningblack holeholographicReissner-Nordström black hole

Mathematics Subject Classification ID

Black holes (83C57) Geometrodynamics and the holographic principle (83E05) Computational methods for problems pertaining to relativity and gravitational theory (83-08)

Cites Work

• Reducing the Dimensionality of Data with Neural Networks
• Learning representations by back-propagating errors
• Gauge theory correlators from non-critical string theory
• Non-perturbative 2 particle scattering amplitudes in \(2+1\) dimensional quantum gravity
• Causal structure of the entanglement renormalization ansatz

Cited In (7)

• Deep learning bulk spacetime from boundary optical conductivity
• Holography as deep learning
• Reconstructing black hole exteriors and interiors using entanglement and complexity
• Black holes and the loss landscape in machine learning
• Gravitational duals from equations of state
• Modeling the complexity of elliptic black hole solution in 4D using Hamiltonian Monte Carlo with stacked neural networks
• Bulk reconstruction of metrics inside black holes by complexity

Uses Software

• PyTorch

This page was built for publication: Deep learning the holographic black hole with charge

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5221253)