XY Neural Networks
This work proposes a novel approach to constructing deep learning architectures with universal applicability, potentially benefiting researchers in machine learning and related fields, though it appears incremental as it adapts an existing physical model.
The authors tackled the problem of building machine learning architectures for complex tasks like speech recognition and visual processing by developing a method based on the XY model's nonlinear blocks from statistical mechanics, achieving high-quality performance on these tasks.
The 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 the 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), allows many possible extensions while at the same time preserving the simplicity of the methodology.