# Performance of Three Slim Variants of The Long Short-Term Memory (LSTM) Layer

## TL;DR

This paper evaluates the performance of three simplified SLIM LSTM variants compared to standard LSTM layers within a neural network architecture, focusing on accuracy and computational efficiency.

## Contribution

It provides a computational analysis of SLIM LSTM variants, demonstrating that some can match standard LSTM performance with potential efficiency gains.

## Key findings

- Some SLIM LSTM variants perform as well as standard LSTM.
- SLIM LSTMs can potentially speed up training and inference.
- The analysis supports the viability of simplified LSTM architectures.

## Abstract

The Long Short-Term Memory (LSTM) layer is an important advancement in the field of neural networks and machine learning, allowing for effective training and impressive inference performance. LSTM-based neural networks have been successfully employed in various applications such as speech processing and language translation. The LSTM layer can be simplified by removing certain components, potentially speeding up training and runtime with limited change in performance. In particular, the recently introduced variants, called SLIM LSTMs, have shown success in initial experiments to support this view. Here, we perform computational analysis of the validation accuracy of a convolutional plus recurrent neural network architecture using comparatively the standard LSTM and three SLIM LSTM layers. We have found that some realizations of the SLIM LSTM layers can potentially perform as well as the standard LSTM layer for our considered architecture.