# On a novel training algorithm for sequence-to-sequence predictive recurrent networks

arXiv: https://arxiv.org/abs/2106.14120 · HTML: https://mlsanity.com/paper/2106.14120/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 3 references that are in the map.
- First posted on arXiv 27 Jun 2021.

## Builds on (most cited first, 2 of 2)

- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [A fast noise filtering algorithm for time series prediction using recurrent neural networks](https://mlsanity.com/paper/2007.08063/) (2020)

## Built on by (most cited first, 1 of 1)

- [It's a super deal -- train recurrent network on noisy data and get smooth prediction free](https://mlsanity.com/paper/2206.04215/) (2022)

## Abstract (arXiv)

Neural networks mapping sequences to sequences (seq2seq) lead to significant progress in machine translation and speech recognition. Their traditional architecture includes two recurrent networks (RNs) followed by a linear predictor. In this manuscript we perform analysis of a corresponding algorithm and show that the parameters of the RNs of the well trained predictive network are not independent of each other. Their dependence can be used to significantly improve the network effectiveness. The traditional seq2seq algorithms require short term memory of a size proportional to the predicted sequence length. This requirement is quite difficult to implement in a neuroscience context. We present a novel memoryless algorithm for seq2seq predictive networks and compare it to the traditional one in the context of time series prediction. We show that the new algorithm is more robust and makes predictions with higher accuracy than the traditional one.