# Learning Longer Memory in Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1412.7753 · HTML: https://mlsanity.com/paper/1412.7753/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2014.

## Built on by (most cited first, 12 of 12)

- [Recurrent Neural Networks and Long Short-Term Memory Networks: Tutorial and Survey](https://mlsanity.com/paper/2304.11461/) (2023)
- [Text classification optimization algorithm based on graph neural network](https://mlsanity.com/paper/2408.15257/) (2024)
- [Slower is Better: Revisiting the Forgetting Mechanism in LSTM for Slower Information Decay](https://mlsanity.com/paper/2105.05944/) (2021)
- [Deep Transfer Learning & Beyond: Transformer Language Models in Information Systems Research](https://mlsanity.com/paper/2110.08975/) (2021)
- [Warming up recurrent neural networks to maximise reachable multistability greatly improves learning](https://mlsanity.com/paper/2106.01001/) (2021)
- [N-gram Prediction and Word Difference Representations for Language Modeling](https://mlsanity.com/paper/2409.03295/) (2024)
- [Revisiting Glorot Initialization for Long-Range Linear Recurrences](https://mlsanity.com/paper/2505.19827/) (2025)
- [Adapting Large Language Models for Character-based Augmentative and Alternative Communication](https://mlsanity.com/paper/2501.10582/) (2025)
- [Spatiotemporal deep learning models for detection of rapid intensification in cyclones](https://mlsanity.com/paper/2506.08397/) (2025)
- [Extending Memory for Language Modelling](https://mlsanity.com/paper/2305.11462/) (2023)
- [A Fault Prognostic System for the Turbine Guide Bearings of a Hydropower Plant Using Long-Short Term Memory (LSTM)](https://mlsanity.com/paper/2407.19040/) (2024)
- [Rotate the Loop: Blockwise Conformality for Looped Transformers](https://mlsanity.com/paper/2610.14030/) (2026)

## Abstract (arXiv)

Recurrent neural network is a powerful model that learns temporal patterns in sequential data. For a long time, it was believed that recurrent networks are difficult to train using simple optimizers, such as stochastic gradient descent, due to the so-called vanishing gradient problem. In this paper, we show that learning longer term patterns in real data, such as in natural language, is perfectly possible using gradient descent. This is achieved by using a slight structural modification of the simple recurrent neural network architecture. We encourage some of the hidden units to change their state slowly by making part of the recurrent weight matrix close to identity, thus forming kind of a longer term memory. We evaluate our model in language modeling experiments, where we obtain similar performance to the much more complex Long Short Term Memory (LSTM) networks (Hochreiter & Schmidhuber, 1997).