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 |
---|---|---|
Language Modelling | 26 | 3.94% |
Sentiment Analysis | 22 | 3.33% |
Time Series Analysis | 21 | 3.18% |
Time Series Forecasting | 20 | 3.03% |
Machine Translation | 14 | 2.12% |
Decision Making | 14 | 2.12% |
Management | 14 | 2.12% |
Activity Recognition | 12 | 1.82% |
Classification | 11 | 1.67% |
Component | Type |
|
---|---|---|
![]() |
Activation Functions | |
![]() |
Activation Functions |