论文标题
非时间序列数据的物理系统
Physical System for Non Time Sequence Data
论文作者
论文摘要
我们提出了一种新颖的方法，将机器学习与神经网络的Jacobian Matrix W.R.T.输入变量。在本文中，我们将基于雅各布的方法扩展到了物理系统，这是人类探索和推理世界的方法，这是因果关系的最高水平。通过与神经ode拟合的功能，我们可以从功能中读取因果结构。该方法还对图节点的连续邻接矩阵强加了重要的辅助约束，并显着降低了图形搜索空间的计算复杂性。
We propose a novelty approach to connect machine learning to causal structure learning by jacobian matrix of neural network w.r.t. input variables. In this paper, we extend the jacobian-based approach to physical system which is the method human explore and reason the world and it is the highest level of causality. By functions fitting with Neural ODE, we can read out causal structure from functions. This method also enforces a important acylicity constraint on continuous adjacency matrix of graph nodes and significantly reduce the computational complexity of search space of graph.
