Multivariate Temporal Autoencoder for Predictive Reconstruction of Deep Sequences
This addresses the problem of handling multi-dimensional temporal data for researchers in time series analysis, but it appears incremental as it builds on existing autoencoder and predictor methods without introducing a new paradigm.
The paper tackled the challenge of predicting and modeling multivariate time series by proposing a multi-branch deep neural network called Multivariate Temporal Autoencoder (MvTAe), which models latent state vectors using a recurrent autoencoder and feeds them into a predictor branch, tested on a synthetic dataset with hidden output targets.
Time series sequence prediction and modelling has proven to be a challenging endeavor in real world datasets. Two key issues are the multi-dimensionality of data and the interaction of independent dimensions forming a latent output signal, as well as the representation of multi-dimensional temporal data inside of a predictive model. This paper proposes a multi-branch deep neural network approach to tackling the aforementioned problems by modelling a latent state vector representation of data windows through the use of a recurrent autoencoder branch and subsequently feeding the trained latent vector representation into a predictor branch of the model. This model is henceforth referred to as Multivariate Temporal Autoencoder (MvTAe). The framework in this paper utilizes a synthetic multivariate temporal dataset which contains dimensions that combine to create a hidden output target.