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

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, several recently introduced variants, called Slim LSTMs, have shown success in initial experiments to support this view. In this paper, we perform computational analysis of the validation accuracy of a convolutional plus recurrent neural network architecture designed to analyze sentiment, using comparatively the standard LSTM and three Slim LSTM layers. We found that some realizations of the Slim LSTM layers can potentially perform as well as the standard LSTM layer for our considered architecture targeted at sentiment analysis.