Understanding LSTM - a tutorial into Long Short-Term Memory Recurrent Neural Networks

By Ralf C. Staudemeyer, Eric Rothstein Morris. arXiv.org, 2019

908 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/c0db083c2e3b862824f9d3eee6908ffce0bfb8fd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chengyu Wang
2. Jun Huang
3. Ming Gao
4. Minghui Qiu
5. Jianing Wang

Citations in the corpus

• DepGraph: Towards Any Structural Pruning (2023, neutral): “In sum, our contribution is a generic pruning scheme towards any structural pruning, termed as Dependency Graph (DepGraph), which allows for automatic parameter grouping and effectively improves the generalizability of structural pruning over various network architectures, including CNNs, RNNs, GNNs”
• TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification (2021, methodology): “A naive approach for obtaining the meta-learner is applying the P-tuning process (Staudemeyer and Morris, 2019) across the M tasks with the M + 1 prompt encoders.”