# Empirical Analysis of Limits for Memory Distance in Recurrent Neural Networks

arXiv: https://arxiv.org/abs/2212.11085 · HTML: https://mlsanity.com/paper/2212.11085/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks](https://mlsanity.com/paper/1701.05923/) (2017)
- [Deep Echo State Network (DeepESN): A Brief Survey](https://mlsanity.com/paper/1712.04323/) (2017)
- [Memory and forecasting capacities of nonlinear recurrent networks](https://mlsanity.com/paper/2004.11234/) (2020)
- [Simplified Gating in Long Short-term Memory (LSTM) Recurrent Neural Networks](https://mlsanity.com/paper/1701.03441/) (2017)

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

- [SwiftQueue: Optimizing Low-Latency Applications with Swift Packet Queuing](https://mlsanity.com/paper/2410.06112/) (2024)

## Abstract (arXiv)

Common to all different kinds of recurrent neural networks (RNNs) is the intention to model relations between data points through time. When there is no immediate relationship between subsequent data points (like when the data points are generated at random, e.g.), we show that RNNs are still able to remember a few data points back into the sequence by memorizing them by heart using standard backpropagation. However, we also show that for classical RNNs, LSTM and GRU networks the distance of data points between recurrent calls that can be reproduced this way is highly limited (compared to even a loose connection between data points) and subject to various constraints imposed by the type and size of the RNN in question. This implies the existence of a hard limit (way below the information-theoretic one) for the distance between related data points within which RNNs are still able to recognize said relation.