Multivariate Temporal Autoencoder for Predictive Reconstruction of Deep Sequences

10/07/2020
by   Jakob Aungiers, et al.
0

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.

READ FULL TEXT
research
01/21/2016

Model-Coupled Autoencoder for Time Series Visualisation

We present an approach for the visualisation of a set of time series tha...
research
05/05/2015

Autoencoding Time Series for Visualisation

We present an algorithm for the visualisation of time series. To that en...
research
10/14/2022

Latent Temporal Flows for Multivariate Analysis of Wearables Data

Increased use of sensor signals from wearable devices as rich sources of...
research
08/19/2022

An Unsupervised Short- and Long-Term Mask Representation for Multivariate Time Series Anomaly Detection

Anomaly detection of multivariate time series is meaningful for system b...
research
06/20/2020

Predicting Temporal Sets with Deep Neural Networks

Given a sequence of sets, where each set contains an arbitrary number of...
research
07/12/2018

Inferring Multi-Dimensional Rates of Aging from Cross-Sectional Data

Modeling how individuals evolve over time is a fundamental problem in th...
research
02/28/2020

Learning Multivariate Hawkes Processes at Scale

Multivariate Hawkes Processes (MHPs) are an important class of temporal ...

Please sign up or login with your details

Forgot password? Click here to reset