Recurrent Neural Networks
Gated Recurrent Unit
Introduced by Cho et al. in Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine TranslationA Gated Recurrent Unit, or GRU, is a type of recurrent neural network. It is similar to an LSTM, but only has two gates - a reset gate and an update gate - and notably lacks an output gate. Fewer parameters means GRUs are generally easier/faster to train than their LSTM counterparts.
Image Source: here
Source: Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Time Series Analysis | 41 | 4.52% |
| Decoder | 36 | 3.96% |
| Text to Speech | 34 | 3.74% |
| Speech Synthesis | 33 | 3.63% |
| Prediction | 26 | 2.86% |
| Deep Learning | 24 | 2.64% |
| Time Series Forecasting | 20 | 2.20% |
| Language Modelling | 20 | 2.20% |
| Sentiment Analysis | 18 | 1.98% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
