arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.13666cs.LGstat.ML
收藏

神经关系推理轨迹重构中的不确定性

Uncertainty in Neural Relational Inference Trajectory Reconstruction

University of Cambridge(剑桥大学)

Vasileios Karavias, Ben Day, Pietro Liò

摘要:

用于多交互轨迹重构的神经网络缺乏估计其输出中的不确定性的能力,这将有助于更好地分析和理解它们所建模的系统。在本文中,我们扩展了因子化神经关系推理模型输出的相空间向量的每个组成部分的平均值和标准差,这与一个适当的损失函数,可以考虑到不确定性。各种损失函数的研究,包括凸化和贝叶斯处理的问题的想法。我们表明,当考虑不确定性时,变量的物理意义是重要的,并证明了在训练过程中难以避免的病态局部极小值的存在。

英文摘要:

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.

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。

↑