Using transformers over large generated datasets, we train models to learn mathematical properties of differential systems, such as local stability, behavior at infinity and controllability. We achieve near perfect prediction of qualitative characteristics, and good approximations of numerical features of the system. This demonstrates that neural networks can learn to perform complex computations, grounded in advanced theory, from examples, without built-in mathematical knowledge.
翻译:用变压器取代大型生成的数据集,我们训练模型来学习差异系统的数学属性,如本地稳定性、无限行为和可控性等。我们几乎完美地预测了质量特征和系统数字特征的近似值。这说明神经网络可以学习基于先进理论、实例和内在数学知识的复杂计算方法。