mLSTM

Multiplicative LSTM

2000년 도입 · 논문 7편에서 사용

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.