# It's a super deal -- train recurrent network on noisy data and get smooth prediction free

arXiv: https://arxiv.org/abs/2206.04215 · HTML: https://mlsanity.com/paper/2206.04215/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 9 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 6 of 6)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Towards a Theory of Evolution as Multilevel Learning](https://mlsanity.com/paper/2110.14602/) (2021)
- [Short note on the behavior of recurrent neural network for noisy dynamical system](https://mlsanity.com/paper/1904.05158/) (2019)
- [A fast noise filtering algorithm for time series prediction using recurrent neural networks](https://mlsanity.com/paper/2007.08063/) (2020)
- [On a novel training algorithm for sequence-to-sequence predictive recurrent networks](https://mlsanity.com/paper/2106.14120/) (2021)

## Abstract (arXiv)

Recent research demonstrate that prediction of time series by predictive recurrent neural networks based on the noisy input generates a smooth anticipated trajectory. We examine influence of the noise component in both the training data sets and the input sequences on network prediction quality. We propose and discuss an explanation of the observed noise compression in the predictive process. We also discuss importance of this property of recurrent networks in the neuroscience context for the evolution of living organisms.