Long Short-Term Memory

301 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Learning-Based Vehicle Behavior Prediction for Autonomous Driving Applications: A Review (2020, background): “any sequence to sequence mapping [52]. However, it is difﬁcult to train this network to learn long sequences in practice due to gradient vanishing or exploding, which is why gated RNNs are introduced [53]. In each cell of these networks, instead of a simple fully connected hidden layer, a gated arch”
LSTM-Based EEG Classification in Motor Imagery Tasks (2018, background): “LSTM, one kind of RNNs, was first proposed by Hochreiter and Schmidhuber [17] and improved by Graves [18].”
A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, background): “h c as the input. The encoder RNN calculates the context vector cby ht = f(xt,ht−1), where ht is the hidden state at time step t, f is a non-linear function such as long-short term memory unit (LSTM) [18] and gated recurrent unit (GRU) [7], and c is the hidden state corresponding to the last word hT”
Neural personalized response generation as domain adaptation (2017, methodology): “Typically, the encoder and decoder are implemented by the GRU [22, 23] or LSTM [24, 25, 26] based RNN.”