AdS/Deep-Learning made easy: simple examples
This work aims to simplify the understanding and application of AdS/Deep-Learning for researchers interested in emergent spacetime as a neural network, representing an incremental step in making this technique more accessible.
This paper introduces the AdS/Deep-Learning technique using simple classical mechanics problems as examples. The method not only provides correct final answers but also offers physical insights into the learning parameters.
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.