It's a super deal -- train recurrent network on noisy data and get smooth prediction free
Not on the map. Why?
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.
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
6 of 9 references.
References · 6
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
- 2021Towards a Theory of Evolution as Multilevel Learningcited by 18
- 2019Short note on the behavior of recurrent neural network for noisy dynamical systemcited by 2
- 2020A fast noise filtering algorithm for time series prediction using recurrent neural networkscited by 2
- 2021On a novel training algorithm for sequence-to-sequence predictive recurrent networkscited by 1
Built on by
Not cited yet.