Neural network architectures based on the classical XY model

Classical XY model is a lattice model of statistical mechanics notable for its universality in the rich hierarchy of the optical, laser, and condensed matter systems. We show how to build complex structures for machine learning based on the XY model's nonlinear blocks. The final target is to reproduce the deep learning architectures, which can perform complicated tasks usually attributed to such architectures: speech recognition, visual processing, or other complex classification types with high quality. We developed a robust and transparent approach for the construction of such models, which has universal applicability (i.e., does not strongly connect to any particular physical system) and allows many possible extensions, while at the same time preserving the simplicity of the methodology.

Automated summary

The classical XY model in statistical mechanics is known for its universality across various physical systems. Researchers have demonstrated how to build complex structures for machine learning based on the model's nonlinear blocks, aiming to reproduce the capabilities of deep learning architectures in tasks like speech recognition and visual processing. They have developed a robust and transparent approach with universal applicability and potential for extensions, while maintaining simplicity in methodology.