Methods › Sequential › Recurrent Neural Networks
Recurrent Neural Networks
The archive attaches this collection's text per method and the copies differ: 3 distinct texts across 3 of the 32 methods here. All are shown, most-carried first (a tie goes to the text carrying Papers with Code's collection boilerplate, then to the longer text); no vote is taken between them.
Text 1, carried by 1 of 32 methods:
Working Memory Models aim to supplement neural networks with a memory module to increase their capability for memorization and allowing them to more easily perform tasks such as retrieving and copying information. Below you can find a continuously updating list of working memory models.
Text 2, carried by 1 of 32 methods:
Language Models are models for predicting the next word or character in a document. Below you can find a continuously updating list of language models.
Text 3, carried by 1 of 32 methods:
Pooling Operations are used to pool features together, often downsampling the feature map to a smaller size. They can also induce favourable properties such as translation invariance in image classification, as well as bring together information from different parts of a network in tasks like object detection (e.g. pooling different scales).
Methods
All 32 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.
| LSTM Long Short-Term Memory | 1997 | 5,448 |
| GRU Gated Recurrent Unit | – | 683 |
| ConvLSTM | – | 145 |
| Pointer Network | – | 105 |
| Residual GRU | – | 66 |
| AWD-LSTM ASGD Weight-Dropped LSTM | – | 52 |
| WaveRNN | – | 26 |
| Neural Turing Machine | – | 22 |
| SRU | – | 16 |
| QRNN Quasi-Recurrent Neural Network | – | 15 |
| SNAIL Simple Neural Attention Meta-Learner | – | 11 |
| LMU Legendre Memory Unit | – | 9 |
| mLSTM Multiplicative LSTM | – | 7 |
| UORO Unbiased Online Recurrent Optimization | – | 6 |
| CRF-RNN | – | 4 |
| ERU Efficient Recurrent Unit | – | 3 |
| Hopfield Layer | – | 3 |
| Unitary RNN | – | 3 |
| CGRU Convolutional GRU | – | 2 |
| Mogrifier LSTM | – | 2 |
| RBPN Recurrent Back Projection Network | – | 2 |
| SHA-RNN Single Headed Attention RNN | – | 2 |
| SRU++ | – | 2 |
| AdaRNN | – | 1 |
| Associative LSTM | – | 1 |
| Deep LSTM Reader | – | 1 |
| Pointer Sentinel-LSTM | – | 1 |
| TSRUc | – | 1 |
| TSRUp | – | 1 |
| TSRUs | – | 1 |
| mRNN Multiplicative RNN | 2011 | 1 |
| rTPNN Recurrent Trend Predictive Neural Network | – | 1 |