Recurrent Neural Networks
Multiplicative LSTM
Introduced by Krause et al. in Multiplicative LSTM for sequence modellingA Multiplicative LSTM (mLSTM) is a recurrent neural network architecture for sequence modelling that combines the long short-term memory (LSTM) and multiplicative recurrent neural network (mRNN) architectures. The mRNN and LSTM architectures can be combined by adding connections from the mRNN’s intermediate state $m_{t}$ to each gating units in the LSTM.
Source: Multiplicative LSTM for sequence modelling
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Language Modelling | 4 | 40.00% |
| Language Modeling | 3 | 30.00% |
| Mamba | 2 | 20.00% |
| Density Estimation | 1 | 10.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
