Gated Recurrent Unit  Cho et al.
There are two variants. The default one is based on 1406.1078v3 and has reset gate applied to hidden state before matrix multiplication. The other one is based on original 1406.1078v1 and has the order reversed.
layer_gru(
object,
units,
activation = "tanh",
recurrent_activation = "hard_sigmoid",
use_bias = TRUE,
return_sequences = FALSE,
return_state = FALSE,
go_backwards = FALSE,
stateful = FALSE,
unroll = FALSE,
reset_after = FALSE,
kernel_initializer = "glorot_uniform",
recurrent_initializer = "orthogonal",
bias_initializer = "zeros",
kernel_regularizer = NULL,
recurrent_regularizer = NULL,
bias_regularizer = NULL,
activity_regularizer = NULL,
kernel_constraint = NULL,
recurrent_constraint = NULL,
bias_constraint = NULL,
dropout = 0,
recurrent_dropout = 0,
input_shape = NULL,
batch_input_shape = NULL,
batch_size = NULL,
dtype = NULL,
name = NULL,
trainable = NULL,
weights = NULL
)
Arguments
object  Model or layer object 
units  Positive integer, dimensionality of the output space. 
activation  Activation function to use. Default: hyperbolic tangent
( 
recurrent_activation  Activation function to use for the recurrent step. 
use_bias  Boolean, whether the layer uses a bias vector. 
return_sequences  Boolean. Whether to return the last output in the output sequence, or the full sequence. 
return_state  Boolean (default FALSE). Whether to return the last state in addition to the output. 
go_backwards  Boolean (default FALSE). If TRUE, process the input sequence backwards and return the reversed sequence. 
stateful  Boolean (default FALSE). If TRUE, the last state for each sample at index i in a batch will be used as initial state for the sample of index i in the following batch. 
unroll  Boolean (default FALSE). If TRUE, the network will be unrolled, else a symbolic loop will be used. Unrolling can speedup a RNN, although it tends to be more memoryintensive. Unrolling is only suitable for short sequences. 
reset_after  GRU convention (whether to apply reset gate after or before matrix multiplication). FALSE = "before" (default), TRUE = "after" (CuDNN compatible). 
kernel_initializer  Initializer for the 
recurrent_initializer  Initializer for the 
bias_initializer  Initializer for the bias vector. 
kernel_regularizer  Regularizer function applied to the 
recurrent_regularizer  Regularizer function applied to the

bias_regularizer  Regularizer function applied to the bias vector. 
activity_regularizer  Regularizer function applied to the output of the layer (its "activation").. 
kernel_constraint  Constraint function applied to the 
recurrent_constraint  Constraint function applied to the

bias_constraint  Constraint function applied to the bias vector. 
dropout  Float between 0 and 1. Fraction of the units to drop for the linear transformation of the inputs. 
recurrent_dropout  Float between 0 and 1. Fraction of the units to drop for the linear transformation of the recurrent state. 
input_shape  Dimensionality of the input (integer) not including the samples axis. This argument is required when using this layer as the first layer in a model. 
batch_input_shape  Shapes, including the batch size. For instance,

batch_size  Fixed batch size for layer 
dtype  The data type expected by the input, as a string ( 
name  An optional name string for the layer. Should be unique in a model (do not reuse the same name twice). It will be autogenerated if it isn't provided. 
trainable  Whether the layer weights will be updated during training. 
weights  Initial weights for layer. 
Details
The second variant is compatible with CuDNNGRU (GPUonly) and allows
inference on CPU. Thus it has separate biases for kernel
and
recurrent_kernel
. Use reset_after = TRUE
and
recurrent_activation = "sigmoid"
.
Input shapes
3D tensor with shape (batch_size, timesteps, input_dim)
,
(Optional) 2D tensors with shape (batch_size, output_dim)
.
Output shape
if
return_state
: a list of tensors. The first tensor is the output. The remaining tensors are the last states, each with shape(batch_size, units)
.if
return_sequences
: 3D tensor with shape(batch_size, timesteps, units)
.else, 2D tensor with shape
(batch_size, units)
.
Masking
This layer supports masking for input data with a variable number
of timesteps. To introduce masks to your data,
use an embedding layer with the mask_zero
parameter
set to TRUE
.
Statefulness in RNNs
You can set RNN layers to be 'stateful', which means that the states computed for the samples in one batch will be reused as initial states for the samples in the next batch. This assumes a onetoone mapping between samples in different successive batches. For intuition behind statefulness, there is a helpful blog post here: http://philipperemy.github.io/kerasstatefullstm/
To enable statefulness:
Specify
stateful = TRUE
in the layer constructor.Specify a fixed batch size for your model. For sequential models, pass
batch_input_shape = c(...)
to the first layer in your model. For functional models with 1 or more Input layers, passbatch_shape = c(...)
to all the first layers in your model. This is the expected shape of your inputs including the batch size. It should be a vector of integers, e.g.c(32, 10, 100)
. For dimensions which can vary (are not known ahead of time), useNULL
in place of an integer, e.g.c(32, NULL, NULL)
.Specify
shuffle = FALSE
when calling fit().
To reset the states of your model, call reset_states()
on either
a specific layer, or on your entire model.
Initial State of RNNs
You can specify the initial state of RNN layers symbolically by calling
them with the keyword argument initial_state
. The value of
initial_state
should be a tensor or list of tensors representing
the initial state of the RNN layer.
You can specify the initial state of RNN layers numerically by
calling reset_states
with the keyword argument states
. The value of
states
should be a numpy array or list of numpy arrays representing
the initial state of the RNN layer.
References
Learning Phrase Representations using RNN EncoderDecoder for Statistical Machine Translation
On the Properties of Neural Machine Translation: EncoderDecoder Approaches
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
See also
Other recurrent layers:
layer_cudnn_gru()
,
layer_cudnn_lstm()
,
layer_lstm()
,
layer_simple_rnn()