Recurrent Neural Networks

Long Short-Term Memory

An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla RNNs through additional cells, input and output gates. Intuitively, vanishing gradients are solved through additional additive components, and forget gate activations, that allow the gradients to flow through the network without vanishing as quickly.

(Image Source here)

(Introduced by Hochreiter and Schmidhuber)


Paper Code Results Date Stars


Task Papers Share
Time Series 53 8.23%
Language Modelling 41 6.37%
Sentiment Analysis 20 3.11%
Machine Translation 18 2.80%
Text Generation 17 2.64%
Time Series Forecasting 16 2.48%
Text Classification 15 2.33%
Question Answering 12 1.86%
Speech Recognition 12 1.86%