Recurrent Neural Filters: Learning Independent Bayesian Filtering Steps for Time Series Prediction

01/23/2019
by   Bryan Lim, et al.
0

Despite the recent popularity of deep generative state space models, few comparisons have been made between network architectures and the inference steps of the Bayesian filtering framework -- with most models simultaneously approximating both state transition and update steps with a single recurrent neural network (RNN). In this paper, we introduce the Recurrent Neural Filter (RNF), a novel recurrent variational autoencoder architecture that learns distinct representations for each Bayesian filtering step, captured by a series of encoders and decoders. Testing this on three real-world time series datasets, we demonstrate that decoupling representations not only improves the accuracy of one-step-ahead forecasts while providing realistic uncertainty estimates, but also facilitates multistep prediction through the separation of encoder stages.

READ FULL TEXT

page 4

page 5

research
04/26/2021

Stochastic Recurrent Neural Network for Multistep Time Series Forecasting

Time series forecasting based on deep architectures has been gaining pop...
research
11/01/2022

Recurrent Neural Networks and Universal Approximation of Bayesian Filters

We consider the Bayesian optimal filtering problem: i.e. estimating some...
research
09/19/2023

Hybrid State Space-based Learning for Sequential Data Prediction with Joint Optimization

We investigate nonlinear prediction/regression in an online setting and ...
research
02/17/2021

POLA: Online Time Series Prediction by Adaptive Learning Rates

Online prediction for streaming time series data has practical use for m...
research
06/03/2021

Deep Probabilistic Time Series Forecasting using Augmented Recurrent Input for Dynamic Systems

The demand of probabilistic time series forecasting has been recently ra...
research
04/20/2018

What's Going On in Neural Constituency Parsers? An Analysis

A number of differences have emerged between modern and classic approach...
research
07/22/2014

Deep Recurrent Neural Networks for Time Series Prediction

Ability of deep networks to extract high level features and of recurrent...

Please sign up or login with your details

Forgot password? Click here to reset