arXiv · 2411.08138
Emergent field theories from neural networks
Abstract
We establish a duality relation between Hamiltonian systems and neural network-based learning systems. We show that the Hamilton's equations for position and momentum variables correspond to the equations governing the activation dynamics of non-trainable variables and the learning dynamics of trainable variables. The duality is then applied to model various field theories using the activation and learning dynamics of neural networks. For Klein-Gordon fields, the corresponding weight tensor is symmetric, while for Dirac fields, the weight tensor must contain an anti-symmetric tensor factor. The dynamical components of the weight and bias tensors correspond, respectively, to the temporal and spatial components of the gauge field.
Explore related subjects
Keep this discovery
Vitaly Vanchurin. 2024-11-12. Emergent field theories from neural networks. https://arxiv.org/abs/2411.08138
Cite the original work for its findings. Save a collection to share your selection of sources.