Discovering Physical Concepts with Neural Networks
Discovering Physical Concepts with Neural Networks
复制标题
DOI：
10.1103/physrevlett.124.010508
复制
发表时间：
2020-01-08
影响因子：
8.6
通讯作者：
del Rio, Lidia
中科院分区：
文献类型：
--
作者：
Iten, Raban;Metger, Tony;del Rio, Lidia
尽管神经网络在解决具体物理问题方面取得了成功，但它们作为科学发现的通用工具仍处于起步阶段。在这里，我们通过在人类物理推理过程之后建模神经网络架构来解决这个问题，这与表示学习有相似之处。这使我们能够在不预先对系统进行假设的情况下，从实验数据中朝着机器辅助科学发现的长期目标取得进展。我们将这种方法应用到玩具示例中，并表明该网络可以找到物理上相关的参数，利用守恒定律进行预测，并有助于获得概念性的见解，例如哥白尼关于太阳系是日心说的结论。
Despite the success of neural networks at solving concrete physics problems, their use as a general-purpose tool for scientific discovery is still in its infancy. Here, we approach this problem by modeling a neural network architecture after the human physical reasoning process, which has similarities to representation learning. This allows us to make progress towards the long-term goal of machine-assisted scientific discovery from experimental data without making prior assumptions about the system. We apply this method to toy examples and show that the network finds the physically relevant parameters, exploits conservation laws to make predictions, and can help to gain conceptual insights, e.g., Copernicus' conclusion that the solar system is heliocentric.