Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks
Neural and Evolutionary Computing
2019-09-23 v1 Computation and Language
Machine Learning
Abstract
Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN) are one of the most powerful dynamic classifiers publicly known. The network itself and the related learning algorithms are reasonably well documented to get an idea how it works. This paper will shed more light into understanding how LSTM-RNNs evolved and why they work impressively well, focusing on the early, ground-breaking publications. We significantly improved documentation and fixed a number of errors and inconsistencies that accumulated in previous publications. To support understanding we as well revised and unified the notation used.
Cite
@article{arxiv.1909.09586,
title = {Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks},
author = {Ralf C. Staudemeyer and Eric Rothstein Morris},
journal= {arXiv preprint arXiv:1909.09586},
year = {2019}
}
Comments
42 pages, 11 figures, tutorial