Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Modelling Relational Time Series using Gaussian Embeddings
Ludovic Dos Santos, Ali Ziat, Ludovic Denoyer, Benjamin Piwowarski, Patrick Gallinari
Nov 03, 2016 (modified: Dec 16, 2016)ICLR 2017 conference submissionreaders: everyone
Abstract:We address the problem of modeling multiple simultaneous time series where the observations are correlated not only inside each series, but among the different series. This problem happens in many domains such as ecology, meteorology, etc. We propose a new dynamical state space model, based on representation learning, for modeling the evolution of such series. The joint relational and temporal dynamics of the series are modeled as Gaussian distributions in a latent space. A decoder maps the latent representations to the observations. The two components (dynamic model and decoder) are jointly trained. Using stochastic representations allows us to model the uncertainty inherent to observations and to predict unobserved values together with a confidence in the prediction.
TL;DR:We learn latent gaussian distributions for modelling correlated series.
Keywords:Applications, Deep learning
Enter your feedback below and we'll get back to you as soon as possible.