Unification of Symmetries Inside Neural Networks: Transformer, Feedforward and Neural ODE

Understanding the inner workings of neural networks, including transformers, remains one of the most challenging puzzles in machine learning. This study introduces a novel approach by applying the principles of gauge symmetries, a key concept in physics, to neural network architectures. By regarding model functions as physical observables, we find that parametric redundancies of various machine learning models can be interpreted as gauge symmetries. We mathematically formulate the parametric redundancies in neural ODEs, and find that their gauge symmetries are …

architectures concept cs.ai cs.lg functions hep-th inside key machine machine learning network networks neural network neural networks novel physics physics.comp-ph study transformer transformers understanding unification