# LSTM with Working Memory

arXiv: https://arxiv.org/abs/1605.01988 · HTML: https://mlsanity.com/paper/1605.01988/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2016.

## Built on by (most cited first, 4 of 4)

- [What is the best RNN-cell structure to forecast each time series behavior?](https://mlsanity.com/paper/2203.07844/) (2022)
- [Android Malware Detection using Machine learning: A Review](https://mlsanity.com/paper/2307.02412/) (2023)
- [Operationalization of Machine Learning with Serverless Architecture: An Industrial Operationalization of Machine Learning with Serverless Architecture: An Industrial Implementation for Harmonized System Code Prediction](https://mlsanity.com/paper/2602.17102/) (2026)
- [An Auto-Scaling Approach for Serverless Environments Based on a Multi-Expert Consensus Mechanism](https://mlsanity.com/paper/2607.15511/) (2026)

## Abstract (arXiv)

Previous RNN architectures have largely been superseded by LSTM, or "Long Short-Term Memory". Since its introduction, there have been many variations on this simple design. However, it is still widely used and we are not aware of a gated-RNN architecture that outperforms LSTM in a broad sense while still being as simple and efficient. In this paper we propose a modified LSTM-like architecture. Our architecture is still simple and achieves better performance on the tasks that we tested on. We also introduce a new RNN performance benchmark that uses the handwritten digits and stresses several important network capabilities.