论文标题
神经关系推理轨迹重建的不确定性
Uncertainty in Neural Relational Inference Trajectory Reconstruction
论文作者
论文摘要
用于多相互作用轨迹重建的神经网络缺乏估计其输出不确定性的能力，这对于更好地分析和理解它们建模的系统非常有用。在本文中，我们将因子化神经关系推理模型扩展到相位空间向量每个组件的平均值和标准偏差，而这些模型与适当的损失函数一起可以解释不确定性。研究了各种损失功能，包括来自凸的想法和对问题的贝叶斯对待。我们表明，在考虑不确定性时，变量的物理含义很重要，并证明了在训练过程中难以避免的病理局部最小值的存在。
Neural networks used for multi-interaction trajectory reconstruction lack the ability to estimate the uncertainty in their outputs, which would be useful to better analyse and understand the systems they model. In this paper we extend the Factorised Neural Relational Inference model to output both a mean and a standard deviation for each component of the phase space vector, which together with an appropriate loss function, can account for uncertainty. A variety of loss functions are investigated including ideas from convexification and a Bayesian treatment of the problem. We show that the physical meaning of the variables is important when considering the uncertainty and demonstrate the existence of pathological local minima that are difficult to avoid during training.
