# Simplified Gating in Long Short-term Memory (LSTM) Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1701.03441 · HTML: https://mlsanity.com/paper/1701.03441/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2017.

## Built on by (most cited first, 6 of 6)

- [What is the best RNN-cell structure to forecast each time series behavior?](https://mlsanity.com/paper/2203.07844/) (2022)
- [Optimum Output Long Short-Term Memory Cell for High-Frequency Trading Forecasting](https://mlsanity.com/paper/2304.09840/) (2023)
- [Empirical Analysis of Limits for Memory Distance in Recurrent Neural Networks](https://mlsanity.com/paper/2212.11085/) (2022)
- [Minion Gated Recurrent Unit for Continual Learning](https://mlsanity.com/paper/2503.06175/) (2025)
- [RLEEGNet: Integrating Brain-Computer Interfaces with Adaptive AI for Intuitive Responsiveness and High-Accuracy Motor Imagery Classification](https://mlsanity.com/paper/2402.09465/) (2024)
- [An Auto-Scaling Approach for Serverless Environments Based on a Multi-Expert Consensus Mechanism](https://mlsanity.com/paper/2607.15511/) (2026)

## Abstract (arXiv)

The standard LSTM recurrent neural networks while very powerful in long-range dependency sequence applications have highly complex structure and relatively large (adaptive) parameters. In this work, we present empirical comparison between the standard LSTM recurrent neural network architecture and three new parameter-reduced variants obtained by eliminating combinations of the input signal, bias, and hidden unit signals from individual gating signals. The experiments on two sequence datasets show that the three new variants, called simply as LSTM1, LSTM2, and LSTM3, can achieve comparable performance to the standard LSTM model with less (adaptive) parameters.