نسخة أولية وصول مفتوح
Dirac-Interconnected Neural Elements: Discovering Modularity in Physical Systems Without Reduction
Deep learning has shown remarkable success in the data-driven modeling of dynamical systems. Much of its success is attributed not to the flexibility of neural networks but to inductive biases based on physical prior knowledge, such as energy conservation and symplecticity. However, existing methods do not fully exploi …