Performance of Three Slim Variants of The Long Short-Term Memory (LSTM) Layer
This work addresses the need for more efficient LSTM layers in neural networks, but it is incremental as it builds on existing SLIM LSTM variants.
The study compared the validation accuracy of a convolutional plus recurrent neural network using standard LSTM and three SLIM LSTM variants, finding that some SLIM LSTM realizations can perform as well as the standard LSTM layer.
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.