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 1905.08494cs.LGstat.ML
收藏

深度签名转换

Deep Signature Transforms

University of Oxford(牛津大学);The Alan Turing Institute(艾伦·图灵研究所)

Patric Bonnier, Patrick Kidger, Imanol Perez Arribas, Cristopher Salvi, Terry Lyons

摘要:

签名是一个无限分级的统计序列,已知将一个数据流映射到一个可忽略的等价类。它是一种以前被视为固定特征变换的变换,在其上可以构建模型。我们提出了一种新的方法,它结合了签名变换与现代深度学习框架的优点。通过在签名变换之前学习流的增强,可以以数据相关的方式选择签名的项。更一般地,我们描述了签名变换如何可以用作神经网络内的任何地方的层。在这种情况下,它可以被解释为池化操作。我们提出的实证实验的结果来支持理论的理由。代码可在https://github.com/patrick-kidger/Deep-Signature-Transforms获得。

英文摘要:

The signature is an infinite graded sequence of statistics known to characterise a stream of data up to a negligible equivalence class. It is a transform which has previously been treated as a fixed feature transformation, on top of which a model may be built. We propose a novel approach which combines the advantages of the signature transform with modern deep learning frameworks. By learning an augmentation of the stream prior to the signature transform, the terms of the signature may be selected in a data-dependent way. More generally, we describe how the signature transform may be used as a layer anywhere within a neural network. In this context it may be interpreted as a pooling operation. We present the results of empirical experiments to back up the theoretical justification. Code available at https://github.com/patrick-kidger/Deep-Signature-Transforms.

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。

↑