Towards a Theory of Quantum Gravity from Neural Networks
Neural network is a dynamical system described by two different types of degrees of freedom: fast-changing non-trainable variables (e.g., state of neurons) and slow-changing trainable variables (e.g., weights and biases). We show that the non-equilibrium dynamics of trainable variables can be descri...
Main Author: | Vitaly Vanchurin |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/24/1/7 |
Similar Items
-
The World as a Neural Network
by: Vitaly Vanchurin
Published: (2020-10-01) -
Pure states statistical mechanics: on its foundations and applications to quantum gravity
by: Anza, F
Published: (2018) -
Automated Detection of Alzheimer’s via Hybrid Classical Quantum Neural Networks
by: Tayyaba Shahwar, et al.
Published: (2022-02-01) -
Predicting quantum advantage by quantum walk with convolutional neural networks
by: Alexey A Melnikov, et al.
Published: (2019-01-01) -
Quantum Graph Neural Network Models for Materials Search
by: Ju-Young Ryu, et al.
Published: (2023-06-01)