arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.04583cs.LG
收藏

神经时空点过程

Neural Spatio-Temporal Point Processes

University of Toronto(多伦多大学);Vector Institute(矢量研究所);Facebook AI Research(脸书人工智能研究室)

Ricky T. Q. Chen, Brandon Amos, Maximilian Nickel

摘要:

我们提出了一类新的时空点过程的参数化,它利用神经常微分方程作为计算方法,并使灵活,高保真模型的离散事件,本地化在连续的时间和空间。我们的方法的核心是连续时间神经网络与两种新型神经架构的组合,即,跳跃和连续时间的注意正规化流。这种方法使我们能够学习空间和时间域的复杂分布,并对观察到的事件历史进行非平凡的条件。我们验证了我们的模型的数据集,从各种各样的背景下,如地震学,流行病学,城市流动性和神经科学。

英文摘要:

We propose a new class of parameterizations for spatio-temporal point processes which leverage Neural ODEs as a computational method and enable flexible, high-fidelity models of discrete events that are localized in continuous time and space. Central to our approach is a combination of continuous-time neural networks with two novel neural architectures, i.e., Jump and Attentive Continuous-time Normalizing Flows. This approach allows us to learn complex distributions for both the spatial and temporal domain and to condition non-trivially on the observed event history. We validate our models on data sets from a wide variety of contexts such as seismology, epidemiology, urban mobility, and neuroscience.

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。

↑