[b:1ykjr02m]Long Short Term Memory networks – usually just called “LSTMs”[/b:1ykjr02m] – are a special kind of RNN, capable of learning long-term dependencies. They were introduced by Hochreiter & Schmidhuber (1997)
[b:1ykjr02m]Long short-term memory (LSTM)[/b:1ykjr02m] is a recurrent neural network (RNN) architecture that remembers values over arbitrary intervals
[url:1ykjr02m]https://en.wikipedia.org/wiki/Long_short-term_memory[/url:1ykjr02m]
[url:1ykjr02m]https://medium.com/towards-data-science/lstm-by-example-using-tensorflow-feb0c1968537[/url:1ykjr02m]
↧