guillaume-chevalier / Linear-Attention-Recurrent-Neural-Network
A recurrent attention module consisting of an LSTM cell which can query its own past cell states by the means of windowed multi-head attention. The formulas are derived from the BN-LSTM and the Transformer Network. The LARNN cell with attention can be easily used inside a loop on the cell state, just like any other RNN. (LARNN)
☆144Updated 6 years ago
Alternatives and similar repositories for Linear-Attention-Recurrent-Neural-Network:
Users that are interested in Linear-Attention-Recurrent-Neural-Network are comparing it to the libraries listed below
- Dilated RNNs in pytorch☆212Updated 5 years ago
- PyTorch implementations of LSTM Variants (Dropout + Layer Norm)