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 1908.08286cs.LGstat.ML
收藏

利用具有对数特征的RNN学习随机微分方程

Learning stochastic differential equations using RNN with log signature features

University College London(伦敦大学学院);University of Oxford(牛津大学)

Shujian Liao, Terry Lyons, Weixin Yang, Hao Ni

摘要:

本文有助于通过评估学习流多模态数据的函数的挑战。我们的论文的结果的核心是两个完全不同的方法来解决这个问题的组合。一个来自于作为流数据表示的签名和日志签名的数学原理技术,而另一个则借鉴了递归神经网络(RNN)的技术。前者管理高采样率流的能力和后者管理大规模非线性相互作用的能力允许混合算法易于编码,更快地训练,并且对于给定的精度具有更低的复杂度。我们说明的方法,通过近似的未知功能作为一个控制微分方程。控制微分方程解的线性泛函是数据流上的自然泛函数类。遵循这种方法,我们提出了一种混合Logsig-RNN算法,可以学习流数据上的泛函。通过对各种数据集(即合成数据、NTU RGB+D 120骨骼动作数据和Chalearn 2013手势数据)的测试,我们的算法实现了出色的准确性,具有优异的效率和鲁棒性。

英文摘要:

This paper contributes to the challenge of learning a function on streamed multimodal data through evaluation. The core of the result of our paper is the combination of two quite different approaches to this problem. One comes from the mathematically principled technology of signatures and log-signatures as representations for streamed data, while the other draws on the techniques of recurrent neural networks (RNN). The ability of the former to manage high sample rate streams and the latter to manage large scale nonlinear interactions allows hybrid algorithms that are easy to code, quicker to train, and of lower complexity for a given accuracy. We illustrate the approach by approximating the unknown functional as a controlled differential equation. Linear functionals on solutions of controlled differential equations are the natural universal class of functions on data streams. Following this approach, we propose a hybrid Logsig-RNN algorithm that learns functionals on streamed data. By testing on various datasets, i.e. synthetic data, NTU RGB+D 120 skeletal action data, and Chalearn2013 gesture data, our algorithm achieves the outstanding accuracy with superior efficiency and robustness.

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。

↑