AdS/CFT as a deep Boltzmann machine

Abstract

We provide a deep Boltzmann machine (DBM) for the AdS/CFT correspondence. Under the philosophy that the bulk spacetime is a neural network, we give a dictionary between those, and obtain a restricted DBM as a discretized bulk scalar field theory in curved geometries. The probability distribution as training data is the generating functional of the boundary quantum field theory, and it trains neural network weights which are the metric of the bulk geometry. The deepest layer implements black hole horizons, and an employed regularization for the weights is an Einstein action. A large $N_c$ limit in holography reduces the DBM to a folded feed-forward architecture. We also neurally implement holographic renormalization into an autoencoder. The DBM for the AdS/CFT may serve as a platform for studying mechanisms of spacetime emergence in holography.

13 pages, 5 figures

References in corpus (23)

• Gauge Theory Correlators from Non-Critical String Theory
• The Large N Limit of Superconformal Field Theories and Supergravity
• Holographic Reconstruction of Spacetime and Renormalization in the AdS/CFT Correspondence
• Eternal Black Holes in AdS
• AdS/CFT Correspondence and Symmetry Breaking
• Entanglement Renormalization and Holography
• Holographic quantum error-correcting codes: Toy models for the bulk/boundary correspondence
• Time Evolution of Entanglement Entropy from Black Hole Interiors
• Highway Networks
• Non-perturbative Lorentzian Quantum Gravity, Causality and Topology Change
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Machine Learning in the String Landscape
• Deep Learning and AdS/CFT
• Evolving neural networks with genetic algorithms to study the String Landscape
• Machine Learning Spatial Geometry from Entanglement Features
• Deep Learning and Holographic QCD
• Holographic Geometry of cMERA for Quantum Quenches and Finite Temperature
• Tensor Network and Black Hole
• Holography as deep learning
• Classification of Standard-like Heterotic-String Vacua
• Vacuum Selection from Cosmology on Networks of String Geometries
• Artificial Neural Network in Cosmic Landscape
• Machine Learning, Deepest Learning: Statistical Data Assimilation Problems

Cited by in corpus (37)

• Machine Learning in Nuclear Physics
• Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models
• Exploring QCD matter in extreme conditions with Machine Learning
• Deep Learning and AdS/QCD
• Machine Learning Holographic Mapping by Neural Network Renormalization Group
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• The Calabi-Yau Landscape: from Geometry, to Physics, to Machine-Learning
• Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
• Deep learning black hole metrics from shear viscosity
• Deriving dilaton potential in improved holographic QCD from meson spectrum
• Neural ODE and Holographic QCD
• Deep learning bulk spacetime from boundary optical conductivity
• Holographic reconstruction of black hole spacetime: machine learning and entanglement entropy
• Learning the black hole metric from holographic conductivity
• Machine Learning Statistical Gravity from Multi-Region Entanglement Entropy
• Entanglement wedge reconstruction and correlation measures in mixed states: modular flows versus quantum recovery channels
• RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior
• Gravitational Duals from Equations of State
• Bulk reconstruction of metrics inside black holes by complexity
• Entanglement Area Law for Shallow and Deep Quantum Neural Network States
• Unification of Symmetries Inside Neural Networks: Transformer, Feedforward and Neural ODE
• Reconstructing black hole exteriors and interiors using entanglement and complexity
• Universes as Big Data
• The Algebraic Structure Underlying Pole-Skipping Points
• Multi-body wave function of ground and low-lying excited states using unornamented deep neural networks
• Constructing and Machine Learning Calabi-Yau Five-folds
• Neural network representation of quantum systems
• Quantum field theories, Markov random fields and machine learning
• Some Open Questions in Quiver Gauge Theory
• Baryons from Mesons: A Machine Learning Perspective
• Generative AI for Brane Configurations and Coamoeba
• Black holes and the loss landscape in machine learning
• Neural Network Complexity of Chaos and Turbulence
• The Autodidactic Universe
• Complexity for deep neural networks and other characteristics of deep feature representations
• Building bulk from Wilson loops
• Learning holographic QCD with unflavored meson spectra