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 1810.04066cs.LGstat.ML
收藏

具有差分高斯过程流的深度学习

Deep learning with differential Gaussian process flows

Helsinki Institute for Information Technology HIIT(赫尔辛基信息技术研究所(HIIT));Aalto University(阿尔托大学)

Pashupati Hegde, Markus Heinonen, Harri Lähdesmäki, Samuel Kaski

摘要:

我们提出了一种新的差分流深度学习范式,它在标准分类或回归函数之前学习输入的随机微分方程变换。微分高斯过程的关键属性是通过无限深,但无穷小的微分场,将离散层概括为动力系统的输入弯曲。我们展示了超越深度高斯过程和神经网络性能的最新结果

英文摘要:

We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function. The key property of differential Gaussian processes is the warping of inputs through infinitely deep, but infinitesimal, differential fields, that generalise discrete layers into a dynamical system. We demonstrate state-of-the-art results that exceed the performance of deep Gaussian processes and neural networks

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。

↑