Recurrent Neural Networks

Multiplicative LSTM

Introduced by Krause et al. in Multiplicative LSTM for sequence modelling

A 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


Paper Code Results Date Stars


Task Papers Share
Density Estimation 1 50.00%
Language Modelling 1 50.00%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign