# Hidden State Approximation in Recurrent Neural Networks Using Continuous Particle Filtering

arXiv: https://arxiv.org/abs/2212.09008 · HTML: https://mlsanity.com/paper/2212.09008/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 20 references that are in the map.
- First posted on arXiv 18 Dec 2022.

## Builds on (most cited first, 3 of 3)

- [Importance Weighted Autoencoders](https://mlsanity.com/paper/1509.00519/) (2015)
- [A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction](https://mlsanity.com/paper/1704.02971/) (2017)
- [Particle Filter Recurrent Neural Networks](https://mlsanity.com/paper/1905.12885/) (2019)

## Abstract (arXiv)

Using historical data to predict future events has many applications in the real world, such as stock price prediction; the robot localization. In the past decades, the Convolutional long short-term memory (LSTM) networks have achieved extraordinary success with sequential data in the related field. However, traditional recurrent neural networks (RNNs) keep the hidden states in a deterministic way. In this paper, we use the particles to approximate the distribution of the latent state and show how it can extend into a more complex form, i.e., the Encoder-Decoder mechanism. With the proposed continuous differentiable scheme, our model is capable of adaptively extracting valuable information and updating the latent state according to the Bayes rule. Our empirical studies demonstrate the effectiveness of our method in the prediction tasks.