Time series source separation with slow flows
arXiv preprint arXiv:2007.10182, 2020•arxiv.org
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.
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.
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.
arxiv.org
以上显示的是最相近的搜索结果。 查看全部搜索结果