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

## TL;DR

This paper introduces Recurrent Neural Filters, a new neural network architecture that learns separate representations for Bayesian filtering steps, improving time series prediction accuracy and uncertainty estimation.

## Contribution

The novel RNF architecture explicitly models individual Bayesian filtering steps with separate encoders and decoders, enhancing interpretability and multistep forecasting.

## Key findings

- Improved one-step-ahead forecast accuracy
- Realistic uncertainty estimates for predictions
- Enhanced multistep prediction capabilities

## Abstract

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 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 the decoupled representations learnt not only improve the accuracy of one-step-ahead forecasts while providing realistic uncertainty estimates, but also facilitate multistep prediction through the separation of encoder stages.