Yin, Z; Barucca, P; (2021) Stochastic Recurrent Neural Network for Multistep Time Series Forecasting. In: Neural Information Processing. (pp. pp. 14-26). Springer: Cham, Switzerland.

Preview

Text Stochastic Recurrent Neural Network for Multistep Time Series Forecasting.pdf - Accepted Version Download (2MB) | Preview

Abstract

Time series forecasting based on deep architectures has been gaining popularity in recent years due to their ability to model complex non-linear temporal dynamics. The recurrent neural network is one such model capable of handling variable-length input and output. In this paper, we leverage recent advances in deep generative models and the concept of state space models to propose a stochastic adaptation of the recurrent neural network for multistep-ahead time series forecasting, which is trained with stochastic gradient variational Bayes. To capture the stochasticity in time series temporal dynamics, we incorporate a latent random variable into the recurrent neural network to make its transition function stochastic. Our model preserves the architectural workings of a recurrent neural network for which all relevant information is encapsulated in its hidden states, and this flexibility allows our model to be easily integrated into any deep architecture for sequential modelling. We test our model on a wide range of datasets from finance to healthcare; results show that the stochastic recurrent neural network consistently outperforms its deterministic counterpart.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as XMLCSVJSON

Archive Staff Only

View Item