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)

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Language Modelling 32 4.58%
Sentence 28 4.01%
Sentiment Analysis 22 3.15%
Time Series Forecasting 20 2.87%
Management 16 2.29%
Machine Translation 14 2.01%
Classification 13 1.86%
Speech Recognition 13 1.86%
Text Generation 12 1.72%

Categories