# AdS/Deep-Learning made easy: simple examples

arXiv: https://arxiv.org/abs/2011.13726 · HTML: https://mlsanity.com/paper/2011.13726/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [Gravitational Duals from Equations of State](https://mlsanity.com/paper/2403.14763/) (2024)
- [Unification of Symmetries Inside Neural Networks: Transformer, Feedforward and Neural ODE](https://mlsanity.com/paper/2402.02362/) (2024)
- [Physics-informed neural network solves minimal surfaces in curved spacetime](https://mlsanity.com/paper/2509.10866/) (2025)
- [Machine-learning emergent spacetime from linear response in future tabletop quantum gravity experiments](https://mlsanity.com/paper/2411.16052/) (2024)
- [Learning the Inverse Ryu--Takayanagi Formula with Transformers](https://mlsanity.com/paper/2511.06387/) (2025)
- [AdS/Deep-Learning made easy II: neural network-based approaches to holography and inverse problems](https://mlsanity.com/paper/2511.22522/) (2025)
- [Machine learning modularity](https://mlsanity.com/paper/2601.01779/) (2026)
- [GlueNN: gluing patchwise analytic solutions with neural networks](https://mlsanity.com/paper/2601.05889/) (2026)
- [Machine Learning Meets High-Energy Nuclear Physics: From Pattern Recognition to Physics-Integrated Discovery](https://mlsanity.com/paper/2610.12293/) (2026)

## Abstract (arXiv)

Deep learning has been widely and actively used in various research areas. Recently, in the gauge/gravity duality, a new deep learning technique so-called the AdS/Deep-Learning (DL) has been proposed [1, 2]. The goal of this paper is to describe the essence of the AdS/DL in the simplest possible setups, for those who want to apply it to the subject of emergent spacetime as a neural network. For prototypical examples, we choose simple classical mechanics problems. This method is a little different from standard deep learning techniques in the sense that not only do we have the right final answers but also obtain a physical understanding of learning parameters.