Qu'est-ce que « Recurrent neural network, long short-term memory » ?

A recurrent neural network reads a sequence one step at a time and carries a hidden state, $h_t = \mathrm{act}(A x_t + C h_{t-1} + c)$. A long short-term memory network (LSTM) adds a cell state updated through gates (input, forget and output, each a sigmoid of $x_t$ and $h_{t-1}$), which lets gradients flow over long sequences (Hochreiter and Schmidhuber, 1997).