Cargando…
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...
Autor principal: | Vanchurin, Vitaly |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8774764/ https://www.ncbi.nlm.nih.gov/pubmed/35052033 http://dx.doi.org/10.3390/e24010007 |
Ejemplares similares
-
The World as a Neural Network
por: Vanchurin, Vitaly
Publicado: (2020) -
Toward a theory of evolution as multilevel learning
por: Vanchurin, Vitaly, et al.
Publicado: (2022) -
Kinetic Quantum Theory of Gravity
por: DeAquino, F
Publicado: (2002) -
Kinetic Quantum Theory of Gravity
por: DeAquino, F
Publicado: (2002) -
Covariant loop quantum gravity: an elementary introduction to quantum gravity and spinfoam theory
por: Rovelli, Carlo, et al.
Publicado: (2014)