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 1603.04713cs.CV
收藏

基于Siamese递归网络的时间序列相似性建模

Modeling Time Series Similarity with Siamese Recurrent Networks

Delft University of Technology(代尔夫特理工大学);Facebook AI Research(脸书人工智能研究院)

Wenjie Pei, David M. J. Tax, Laurens van der Maaten

摘要:

测量时间序列之间相似性的传统技术是基于手工制作的相似性度量,而最近基于学习的方法无法利用外部监督。我们结合了时间序列建模和度量学习的思想,并研究了siamese递归网络(SRN),该网络最大限度地减少了分类损失,以学习时间序列之间的良好相似性度量。具体来说,我们的方法学习每个时间序列的向量表示,以这样一种方式,类似的时间序列由类似的表示建模,不同的时间序列由不同的表示建模。因为它是一个相似性预测模型,所以SRN特别适合于具有挑战性的场景,例如签名识别,其中每个人都是一个单独的类,每个类的例子很少。我们展示了潜在的优点,SRN在域内和域外的分类实验,并在一次性学习实验的任务,如签名,语音和手语识别。

英文摘要:

Traditional techniques for measuring similarities between time series are based on handcrafted similarity measures, whereas more recent learning-based approaches cannot exploit external supervision. We combine ideas from time-series modeling and metric learning, and study siamese recurrent networks (SRNs) that minimize a classification loss to learn a good similarity measure between time series. Specifically, our approach learns a vectorial representation for each time series in such a way that similar time series are modeled by similar representations, and dissimilar time series by dissimilar representations. Because it is a similarity prediction models, SRNs are particularly well-suited to challenging scenarios such as signature recognition, in which each person is a separate class and very few examples per class are available. We demonstrate the potential merits of SRNs in within-domain and out-of-domain classification experiments and in one-shot learning experiments on tasks such as signature, voice, and sign language recognition.

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。

↑