用于高维类别观测空间预测的流式高斯狄利克雷随机场
Streaming Gaussian Dirichlet Random Fields for Spatial Predictions of High Dimensional Categorical Observations
AI总结:
本文提出流式高斯狄利克雷随机场(S-GDRF),用于高效建模稀疏高维类别观测流,在有界时间复杂度下实现快速推理,并在浮游生物图像数据上取得优于变分高斯过程的预测精度,为高维类别观测的信息路径规划奠定基础。
摘要:
我们提出流式高斯狄利克雷随机场(S-GDRF)模型,这是一种对时空分布、稀疏、高维类别观测流进行建模的新方法。该方法能够高效学习时空数据中的全局和局部模式,从而在有界时间复杂度下实现快速推理和查询。利用经神经网络分类的浮游生物图像高分辨率数据序列,我们证明了与变分高斯过程(VGP)相比,该方法能够做出更准确的预测,并能从流式类别数据中学习观测的预测分布。S-GDRF为在高维类别观测上实现高效的信息路径规划打开了大门,而这一点在此之前一直不可行。
英文摘要:
We present the Streaming Gaussian Dirichlet Random Field (S-GDRF) model, a novel approach for modeling a stream of spatiotemporally distributed, sparse, high-dimensional categorical observations. The proposed approach efficiently learns global and local patterns in spatiotemporal data, allowing for fast inference and querying with a bounded time complexity. Using a high-resolution data series of plankton images classified with a neural network, we demonstrate the ability of the approach to make more accurate predictions compared to a Variational Gaussian Process (VGP), and to learn a predictive distribution of observations from streaming categorical data. S-GDRFs open the door to enabling efficient informative path planning over high-dimensional categorical observations, which until now has not been feasible.
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。