Hamilton神经网络
Hamiltonian Neural Networks
摘要:
尽管神经网络得到了广泛的应用,但它们仍然很难学习基本的物理定律。我们如何才能赋予他们更好的归纳偏见呢?在本文中,我们从哈密顿力学中获得灵感,以无监督的方式训练学习和尊重精确守恒律的模型。我们评估我们的模型上的问题,能量守恒是很重要的,包括两体问题和像素观察的钟摆。我们的模型比常规神经网络训练得更快,泛化能力更好。一个有趣的副作用是,我们的模型在时间上是完全可逆的。
英文摘要:
Even though neural networks enjoy widespread use, they still struggle to learn the basic laws of physics. How might we endow them with better inductive biases? In this paper, we draw inspiration from Hamiltonian mechanics to train models that learn and respect exact conservation laws in an unsupervised manner. We evaluate our models on problems where conservation of energy is important, including the two-body problem and pixel observations of a pendulum. Our model trains faster and generalizes better than a regular neural network. An interesting side effect is that our model is perfectly reversible in time.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。