Deep Learning with Keras

Recurrent neural networks — simple, LSTM, and GRU

Recurrent neural networks are a class of neural networks that exploit the sequential nature of their input. Such inputs could be a text, a speech, time series, and anything else where the occurrence of an element in the sequence is dependent on the elements that appeared before it. We will discuss simple, LSTM, and GRU recurrent neural networks in Chapter 6, Recurrent Neural Network — RNN. Here you can see some prototypes with a definition of the parameters:

keras.layers.recurrent.Recurrent(return_sequences=False, go_backwards=False, stateful=False, unroll=False, implementation=0)keras.layers.recurrent.SimpleRNN(units, activation='tanh', use_bias=True, kernel_initializer='glorot_uniform' ...