arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.10264cs.LGstat.ML
收藏

顺序神经过程

Sequential Neural Processes

Rutgers University(罗格斯大学);SAP(思爱普);ETRI(韩国电子通信研究院)

Gautam Singh, Jaesik Yoon, Youngsung Son, Sungjin Ahn

摘要:

神经过程结合了神经网络和高斯过程的优势,实现了随机过程的灵活学习和快速预测。然而,一大类问题包括神经过程(NP)没有明确考虑的随机过程序列中的潜在时间依赖结构。在本文中,我们提出了顺序神经过程(SNP),其中包括一个时间的随机过程的状态转换模型,从而扩展其建模能力的动态随机过程。在将SNP应用于动态三维场景建模中,我们引入了时态生成查询网络。据我们所知,这是第一个可以处理3D场景的时间动态的4D模型。在实验中,我们评估所提出的方法在动态(非平稳)回归和4D场景推理和渲染。

英文摘要:

Neural Processes combine the strengths of neural networks and Gaussian processes to achieve both flexible learning and fast prediction in stochastic processes. However, a large class of problems comprises underlying temporal dependency structures in a sequence of stochastic processes that Neural Processes (NP) do not explicitly consider. In this paper, we propose Sequential Neural Processes (SNP) which incorporates a temporal state-transition model of stochastic processes and thus extends its modeling capabilities to dynamic stochastic processes. In applying SNP to dynamic 3D scene modeling, we introduce the Temporal Generative Query Networks. To our knowledge, this is the first 4D model that can deal with the temporal dynamics of 3D scenes. In experiments, we evaluate the proposed methods in dynamic (non-stationary) regression and 4D scene inference and rendering.

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。

↑