慢流时间序列声源分离
Time Series Source Separation with Slow Flows
摘要:
在本文中,我们表明,慢特征分析(SFA),一种常见的时间序列分解方法,自然适合基于流的模型(FBM)框架,一种可逆的神经潜变量模型。基于盲声源分离的最新进展,我们表明,这样一个适合的时间序列分解识别。
英文摘要:
In this paper, we show that slow feature analysis (SFA), a common time series decomposition method, naturally fits into the flow-based models (FBM) framework, a type of invertible neural latent variable models. Building upon recent advances on blind source separation, we show that such a fit makes the time series decomposition identifiable.
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。