DeepAI AI Chat
Log In Sign Up

RECOWNs: Probabilistic Circuits for Trustworthy Time Series Forecasting

by   Nils Thoma, et al.

Time series forecasting is a relevant task that is performed in several real-world scenarios such as product sales analysis and prediction of energy demand. Given their accuracy performance, currently, Recurrent Neural Networks (RNNs) are the models of choice for this task. Despite their success in time series forecasting, less attention has been paid to make the RNNs trustworthy. For example, RNNs can not naturally provide an uncertainty measure to their predictions. This could be extremely useful in practice in several cases e.g. to detect when a prediction might be completely wrong due to an unusual pattern in the time series. Whittle Sum-Product Networks (WSPNs), prominent deep tractable probabilistic circuits (PCs) for time series, can assist an RNN with providing meaningful probabilities as uncertainty measure. With this aim, we propose RECOWN, a novel architecture that employs RNNs and a discriminant variant of WSPNs called Conditional WSPNs (CWSPNs). We also formulate a Log-Likelihood Ratio Score as better estimation of uncertainty that is tailored to time series and Whittle likelihoods. In our experiments, we show that RECOWNs are accurate and trustworthy time series predictors, able to "know when they do not know".


Position-based Content Attention for Time Series Forecasting with Sequence-to-sequence RNNs

We propose here an extended attention model for sequence-to-sequence rec...

R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting

Multivariate time-series modeling and forecasting is an important proble...

A Worrying Analysis of Probabilistic Time-series Models for Sales Forecasting

Probabilistic time-series models become popular in the forecasting field...

Bidirectional Recurrent Neural Networks as Generative Models - Reconstructing Gaps in Time Series

Bidirectional recurrent neural networks (RNN) are trained to predict bot...

An empirical study of neural networks for trend detection in time series

Detecting structure in noisy time series is a difficult task. One intuit...

On Error Correction Neural Networks for Economic Forecasting

Recurrent neural networks (RNNs) are more suitable for learning non-line...

Fast ES-RNN: A GPU Implementation of the ES-RNN Algorithm

Due to their prevalence, time series forecasting is crucial in multiple ...