Gated recurrent unit (GRU) layer
A GRU layer learns dependencies between time steps in time series and sequence data.
creates a GRU layer and sets the layer
= gruLayer(numHiddenUnits
)NumHiddenUnits
property.
sets additional layer
= gruLayer(numHiddenUnits
,Name,Value
)OutputMode
, Activations, State, Parameters and Initialization, Learning Rate and Regularization, and Name
properties using one or more namevalue pair arguments.
You can specify multiple namevalue pair arguments. Enclose each property name in
quotes.
NumHiddenUnits
— Number of hidden unitsNumber of hidden units (also known as the hidden size), specified as a positive integer.
The number of hidden units corresponds to the amount of information remembered between time steps (the hidden state). The hidden state can contain information from all previous time steps, regardless of the sequence length. If the number of hidden units is too large, then the layer might overfit to the training data. This value can vary from a few dozen to a few thousand.
The hidden state does not limit the number of time steps that are processed in an
iteration. To split your sequences into smaller sequences for training, use the
'SequenceLength'
option in trainingOptions
.
Example: 200
OutputMode
— Output mode'sequence'
(default)  'last'
Output mode, specified as one of the following:
'sequence'
– Output the complete sequence.
'last'
– Output the last time step of the
sequence.
HasStateInputs
— Flag for state inputs to layer0
(false) (default)  1
(true)Flag for state inputs to the layer, specified as 1
(true) or
0
(false).
If the HasStateInputs
property is 0
(false), then the layer has one input with name 'in'
, which corresponds to the input data. In this case, the layer uses the HiddenState
property for the layer operation.
If the HasStateInputs
property is 1
(true), then the layer has two inputs with names 'in'
and 'hidden'
, which correspond to the input data and hidden state, respectively. In this case, the layer uses the values passed to these inputs for the layer operation. If HasStateInputs
is 1
(true), then the HiddenState
property must be empty.
HasStateOutputs
— Flag for state outputs from layer0
(false) (default)  1
(true)Flag for state outputs from the layer, specified as true
or
false
.
If the HasStateOutputs
property is 0
(false), then the
layer has one output with name 'out'
, which corresponds to the output
data.
If the HasStateOutputs
property is 1
(true), then the
layer has two outputs with names 'out'
and
'hidden'
, which correspond to the output data and hidden
state, respectively. In this case, the layer also outputs the state values computed
during the layer operation.
ResetGateMode
— Reset gate mode'aftermultiplication'
(default)  'beforemultiplication'
 'recurrentbiasaftermultiplication'
Reset gate mode, specified as one of the following:
'aftermultiplication'
– Apply reset gate after matrix
multiplication. This option is cuDNN compatible.
'beforemultiplication'
– Apply reset gate before matrix
multiplication.
'recurrentbiasaftermultiplication'
– Apply reset gate
after matrix multiplication and use an additional set of bias terms for the
recurrent weights.
For more information about the reset gate calculations, see Gated Recurrent Unit Layer.
InputSize
— Input size'auto'
(default)  positive integer Input size, specified as a positive integer or 'auto'
. If InputSize
is 'auto'
, then the software automatically assigns the input size at training time.
Example: 100
StateActivationFunction
— Activation function to update the hidden state'tanh'
(default)  'softsign'
Activation function to update the hidden state, specified as one of the following:
'tanh'
– Use the hyperbolic tangent function
(tanh).
'softsign'
– Use the softsign function $$\text{softsign}(x)=\frac{x}{1+\leftx\right}$$.
The layer uses this option as the function $${\sigma}_{s}$$ in the calculations to update the hidden state.
GateActivationFunction
— Activation function to apply to the gates'sigmoid'
(default)  'hardsigmoid'
Activation function to apply to the gates, specified as one of the following:
'sigmoid'
– Use the sigmoid function $$\sigma (x)={(1+{e}^{x})}^{1}$$.
'hardsigmoid'
– Use the hard sigmoid function
$$\sigma (x)=\{\begin{array}{cc}\begin{array}{l}0\hfill \\ 0.2x+0.5\hfill \\ 1\hfill \end{array}& \begin{array}{l}\text{if}x2.5\hfill \\ \text{if}2.5\le x\le 2.5\hfill \\ \text{if}x2.5\hfill \end{array}\end{array}.$$
The layer uses this option as the function $${\sigma}_{g}$$ in the calculations for the layer gates.
HiddenState
— Hidden stateHidden state to use in the layer operation, specified as a
NumHiddenUnits
by1 numeric vector. This value corresponds to the
initial hidden state when data is passed to the layer.
After setting this property manually, calls to the resetState
function set the hidden state to this value.
If HasStateInputs
is true
, then
the HiddenState
property must be empty.
InputWeightsInitializer
— Function to initialize input weights'glorot'
(default)  'he'
 'orthogonal'
 'narrownormal'
 'zeros'
 'ones'
 function handleFunction to initialize the input weights, specified as one of the following:
'glorot'
– Initialize the input weights with the Glorot
initializer [2] (also known as Xavier
initializer). The Glorot initializer independently samples from a uniform
distribution with zero mean and variance 2/(InputSize +
numOut)
, where numOut = 3*NumHiddenUnits
.
'he'
– Initialize the input weights with the He
initializer [3]. The He initializer
samples from a normal distribution with zero mean and variance
2/InputSize
.
'orthogonal'
– Initialize the input weights with
Q, the orthogonal matrix given by the QR decomposition of
Z = QR for a random
matrix Z sampled from a unit normal distribution. [4]
'narrownormal'
– Initialize the input weights by
independently sampling from a normal distribution with zero mean and standard
deviation 0.01.
'zeros'
– Initialize the input weights with zeros.
'ones'
– Initialize the input weights with ones.
Function handle – Initialize the input weights with a custom function. If
you specify a function handle, then the function must be of the form
weights = func(sz)
, where sz
is the size
of the input weights.
The layer only initializes the input weights when the
InputWeights
property is empty.
Data Types: char
 string
 function_handle
RecurrentWeightsInitializer
— Function to initialize recurrent weights'orthogonal'
(default)  'glorot'
 'he'
 'narrownormal'
 'zeros'
 'ones'
 function handleFunction to initialize the recurrent weights, specified as one of the following:
'orthogonal'
– Initialize the recurrent weights with
Q, the orthogonal matrix given by the QR decomposition of
Z = QR for a random
matrix Z sampled from a unit normal distribution. [4]
'glorot'
– Initialize the recurrent weights with the
Glorot initializer [2] (also known as Xavier
initializer). The Glorot initializer independently samples from a uniform
distribution with zero mean and variance 2/(numIn + numOut)
,
where numIn = NumHiddenUnits
and numOut =
3*NumHiddenUnits
.
'he'
– Initialize the recurrent weights with the He
initializer [3]. The He initializer
samples from a normal distribution with zero mean and variance
2/NumHiddenUnits
.
'narrownormal'
– Initialize the recurrent weights by
independently sampling from a normal distribution with zero mean and standard
deviation 0.01.
'zeros'
– Initialize the recurrent weights with zeros.
'ones'
– Initialize the recurrent weights with
ones.
Function handle – Initialize the recurrent weights with a custom function.
If you specify a function handle, then the function must be of the form
weights = func(sz)
, where sz
is the size
of the recurrent weights.
The layer only initializes the recurrent weights when the
RecurrentWeights
property is empty.
Data Types: char
 string
 function_handle
BiasInitializer
— Function to initialize bias'zeros'
(default)  'narrownormal'
 'ones'
 function handleFunction to initialize the bias, specified as one of the following:
zeros'
– Initialize the bias with zeros.
'narrownormal'
– Initialize the bias by independently
sampling from a normal distribution with zero mean and standard deviation
0.01.
'ones'
– Initialize the bias with ones.
Function handle – Initialize the bias with a custom function. If you specify
a function handle, then the function must be of the form bias =
func(sz)
, where sz
is the size of the
bias.
The layer only initializes the bias when the Bias
property is
empty.
Data Types: char
 string
 function_handle
InputWeights
— Input weights[]
(default)  matrixInput weights, specified as a matrix.
The input weight matrix is a concatenation of the three input weight matrices for the components in the GRU layer. The three matrices are concatenated vertically in the following order:
Reset gate
Update gate
Candidate state
The input weights are learnable parameters. When training a network, if InputWeights
is nonempty, then trainNetwork
uses the InputWeights
property as the initial value. If InputWeights
is empty, then trainNetwork
uses the initializer specified by InputWeightsInitializer
.
At training time, InputWeights
is a
3*NumHiddenUnits
byInputSize
matrix.
RecurrentWeights
— Recurrent weights[]
(default)  matrixRecurrent weights, specified as a matrix.
The recurrent weight matrix is a concatenation of the three recurrent weight matrices for the components in the GRU layer. The three matrices are vertically concatenated in the following order:
Reset gate
Update gate
Candidate state
The recurrent weights are learnable parameters. When training a network, if RecurrentWeights
is nonempty, then trainNetwork
uses the RecurrentWeights
property as the initial value. If RecurrentWeights
is empty, then trainNetwork
uses the initializer specified by RecurrentWeightsInitializer
.
At training time RecurrentWeights
is a
3*NumHiddenUnits
byNumHiddenUnits
matrix.
Bias
— Layer biases[]
(default)  numeric vectorLayer biases for the GRU layer, specified as a numeric vector.
If ResetGateMode
is
'aftermultiplication'
or
'beforemultiplication'
, then the bias vector is a concatenation
of three bias vectors for the components in the GRU layer. The three vectors are
concatenated vertically in the following order:
Reset gate
Update gate
Candidate state
In this case, at training time, Bias
is a
3*NumHiddenUnits
by1 numeric vector.
If ResetGateMode
is
recurrentbiasaftermultiplication'
, then the bias vector is a
concatenation of six bias vectors for the components in the GRU layer. The six vectors
are concatenated vertically in the following order:
Reset gate
Update gate
Candidate state
Reset gate (recurrent bias)
Update gate (recurrent bias)
Candidate state (recurrent bias)
In this case, at training time, Bias
is a
6*NumHiddenUnits
by1 numeric vector.
The layer biases are learnable parameters. When you train a
network, if Bias
is nonempty, then trainNetwork
uses the Bias
property as the
initial value. If Bias
is empty, then
trainNetwork
uses the initializer specified by BiasInitializer
.
For more information about the reset gate calculations, see Gated Recurrent Unit Layer.
InputWeightsLearnRateFactor
— Learning rate factor for input weightsLearning rate factor for the input weights, specified as a numeric scalar or a 1by3 numeric vector.
The software multiplies this factor by the global learning rate to determine the learning rate factor for the input weights of the layer. For example, if InputWeightsLearnRateFactor
is 2, then the learning rate factor for the input weights of the layer is twice the current global learning rate. The software determines the global learning rate based on the settings specified with the trainingOptions
function.
To control the value of the learning rate factor for the three individual matrices
in InputWeights
, specify a 1by3 vector. The entries of
InputWeightsLearnRateFactor
correspond to the learning rate
factor of the following:
Reset gate
Update gate
Candidate state
To specify the same value for all the matrices, specify a nonnegative scalar.
Example: 2
Example:
[1 2 1]
RecurrentWeightsLearnRateFactor
— Learning rate factor for recurrent weightsLearning rate factor for the recurrent weights, specified as a numeric scalar or a 1by3 numeric vector.
The software multiplies this factor by the global learning rate to determine the learning rate for the recurrent weights of the layer. For example, if RecurrentWeightsLearnRateFactor
is 2, then the learning rate for the recurrent weights of the layer is twice the current global learning rate. The software determines the global learning rate based on the settings specified with the trainingOptions
function.
To control the value of the learning rate factor for the three individual matrices
in RecurrentWeights
, specify a 1by3 vector. The entries of
RecurrentWeightsLearnRateFactor
correspond to the learning rate
factor of the following:
Reset gate
Update gate
Candidate state
To specify the same value for all the matrices, specify a nonnegative scalar.
Example: 2
Example:
[1 2 1]
BiasLearnRateFactor
— Learning rate factor for biasesLearning rate factor for the biases, specified as a nonnegative scalar or a 1by3 numeric vector.
The software multiplies this factor by the global learning rate
to determine the learning rate for the biases in this layer. For example, if
BiasLearnRateFactor
is 2
, then the learning rate for
the biases in the layer is twice the current global learning rate. The software determines the
global learning rate based on the settings you specify using the trainingOptions
function.
To control the value of the learning rate factor for the three individual vectors
in Bias
, specify a 1by3 vector. The entries of
BiasLearnRateFactor
correspond to the learning rate factor of
the following:
Reset gate
Update gate
Candidate state
If ResetGateMode
is
'recurrentbiasaftermultiplication'
, then the software uses the
same vector for the recurrent bias vectors.
To specify the same value for all the vectors, specify a nonnegative scalar.
Example:
2
Example:
[1 2 1]
InputWeightsL2Factor
— L2 regularization factor for input weightsL2 regularization factor for the input weights, specified as a numeric scalar or a 1by3 numeric vector.
The software multiplies this factor by the global L2 regularization factor to determine the L2 regularization factor for the input weights of the layer. For example, if InputWeightsL2Factor
is 2, then the L2 regularization factor for the input weights of the layer is twice the current global L2 regularization factor. The software determines the L2 regularization factor based on the settings specified with the trainingOptions
function.
To control the value of the L2 regularization factor for the three individual
matrices in InputWeights
, specify a 1by3 vector. The entries of
InputWeightsL2Factor
correspond to the L2 regularization factor
of the following:
Reset gate
Update gate
Candidate state
To specify the same value for all the matrices, specify a nonnegative scalar.
Example: 2
Example:
[1 2 1]
RecurrentWeightsL2Factor
— L2 regularization factor for recurrent weightsL2 regularization factor for the recurrent weights, specified as a numeric scalar or a 1by3 numeric vector.
The software multiplies this factor by the global L2 regularization factor to determine the L2 regularization factor for the recurrent weights of the layer. For example, if RecurrentWeightsL2Factor
is 2, then the L2 regularization factor for the recurrent weights of the layer is twice the current global L2 regularization factor. The software determines the L2 regularization factor based on the settings specified with the trainingOptions
function.
To control the value of the L2 regularization factor for the three individual
matrices in RecurrentWeights
, specify a 1by3 vector. The
entries of RecurrentWeightsL2Factor
correspond to the L2
regularization factor of the following:
Reset gate
Update gate
Candidate state
To specify the same value for all the matrices, specify a nonnegative scalar.
Example: 2
Example:
[1 2 1]
BiasL2Factor
— L2 regularization factor for biasesL2 regularization factor for the biases, specified as a nonnegative scalar or a 1by3 numeric vector.
The software multiplies this factor by the global
L_{2} regularization factor to determine the
L_{2} regularization for the biases in this
layer. For example, if BiasL2Factor
is 2
, then the
L_{2} regularization for the biases in this layer
is twice the global L_{2} regularization factor. You can
specify the global L_{2} regularization factor using the
trainingOptions
function.
To control the value of the L2 regularization factor for the individual vectors in
Bias
, specify a 1by3 vector. The entries of
BiasL2Factor
correspond to the L2 regularization factor of the
following:
Reset gate
Update gate
Candidate state
If ResetGateMode
is
'recurrentbiasaftermultiplication'
, then the software uses the
same vector for the recurrent bias vectors.
To specify the same value for all the vectors, specify a nonnegative scalar.
Example:
2
Example:
[1 2 1]
Name
— Layer name''
(default)  character vector  string scalar
Layer name, specified as a character vector or a string scalar.
For Layer
array input, the trainNetwork
,
assembleNetwork
, layerGraph
, and
dlnetwork
functions automatically assign names to layers with
Name
set to ''
.
Data Types: char
 string
NumInputs
— Number of inputs1
 2
Number of inputs of the layer.
If the HasStateInputs
property is 0
(false), then the layer has one input with name 'in'
, which corresponds to the input data. In this case, the layer uses the HiddenState
property for the layer operation.
If the HasStateInputs
property is 1
(true), then the layer has two inputs with names 'in'
and 'hidden'
, which correspond to the input data and hidden state, respectively. In this case, the layer uses the values passed to these inputs for the layer operation. If HasStateInputs
is 1
(true), then the HiddenState
property must be empty.
Data Types: double
InputNames
— Input names{'in'}
 {'in','hidden'}
Input names of the layer.
If the HasStateInputs
property is 0
(false), then the layer has one input with name 'in'
, which corresponds to the input data. In this case, the layer uses the HiddenState
property for the layer operation.
If the HasStateInputs
property is 1
(true), then the layer has two inputs with names 'in'
and 'hidden'
, which correspond to the input data and hidden state, respectively. In this case, the layer uses the values passed to these inputs for the layer operation. If HasStateInputs
is 1
(true), then the HiddenState
property must be empty.
NumOutputs
— Number of outputs1
 2
Number of outputs of the layer.
If the HasStateOutputs
property is 0
(false), then the
layer has one output with name 'out'
, which corresponds to the output
data.
If the HasStateOutputs
property is 1
(true), then the
layer has two outputs with names 'out'
and
'hidden'
, which correspond to the output data and hidden
state, respectively. In this case, the layer also outputs the state values computed
during the layer operation.
Data Types: double
OutputNames
— Output names{'out'}
 {'out','hidden'}
Output names of the layer.
If the HasStateOutputs
property is 0
(false), then the
layer has one output with name 'out'
, which corresponds to the output
data.
If the HasStateOutputs
property is 1
(true), then the
layer has two outputs with names 'out'
and
'hidden'
, which correspond to the output data and hidden
state, respectively. In this case, the layer also outputs the state values computed
during the layer operation.
Create a GRU layer with the name 'gru1'
and 100 hidden units.
layer = gruLayer(100,'Name','gru1')
layer = GRULayer with properties: Name: 'gru1' InputNames: {'in'} OutputNames: {'out'} NumInputs: 1 NumOutputs: 1 HasStateInputs: 0 HasStateOutputs: 0 Hyperparameters InputSize: 'auto' NumHiddenUnits: 100 OutputMode: 'sequence' StateActivationFunction: 'tanh' GateActivationFunction: 'sigmoid' ResetGateMode: 'aftermultiplication' Learnable Parameters InputWeights: [] RecurrentWeights: [] Bias: [] State Parameters HiddenState: [] Show all properties
Include a GRU layer in a Layer
array.
inputSize = 12;
numHiddenUnits = 100;
numClasses = 9;
layers = [ ...
sequenceInputLayer(inputSize)
gruLayer(numHiddenUnits)
fullyConnectedLayer(numClasses)
softmaxLayer
classificationLayer]
layers = 5x1 Layer array with layers: 1 '' Sequence Input Sequence input with 12 dimensions 2 '' GRU GRU with 100 hidden units 3 '' Fully Connected 9 fully connected layer 4 '' Softmax softmax 5 '' Classification Output crossentropyex
A GRU layer learns dependencies between time steps in time series and sequence data.
The hidden state of the layer at time step t contains the output of the GRU layer for this time step. At each time step, the layer adds information to or removes information from the state. The layer controls these updates using gates.
The following components control the hidden state of the layer.
Component  Purpose 

Reset gate (r)  Control level of state reset 
Update gate (z)  Control level of state update 
Candidate state ($$\tilde{h}$$)  Control level of update added to hidden state 
The learnable weights of a GRU layer are the input weights W
(InputWeights
), the recurrent weights R
(RecurrentWeights
), and the bias b
(Bias
). If the ResetGateMode
property is 'recurrentbiasaftermultiplication'
, then the gate and
state calculations require two sets of bias values. The matrices W and
R are concatenations of the input weights and the recurrent weights of
each component, respectively. These matrices are concatenated as follows:
$$W=\left[\begin{array}{c}{W}_{r}\\ {W}_{z}\\ {W}_{\tilde{h}}\end{array}\right],R=\left[\begin{array}{c}{R}_{r}\\ {R}_{z}\\ {R}_{\tilde{h}}\end{array}\right],$$
where r, z, and $$\tilde{h}$$ denote the reset gate, update gate, and candidate state, respectively.
The bias vector depends on the ResetGateMode
property. If ResetGateMode
is
'aftermutliplication'
or 'beforemultiplication'
,
then the bias vector is a concatenation of three vectors:
$$b=\left[\begin{array}{c}{b}_{{W}_{r}}\\ {b}_{{W}_{z}}\\ {b}_{{W}_{\tilde{h}}}\end{array}\right],$$
where the subscript W indicates that this is the bias corresponding to the input weights multiplication.
If ResetGateMode
is
'recurrentbiasaftermultiplication'
, then the bias vector is a
concatenation of six vectors:
$$b=\left[\begin{array}{c}{b}_{{W}_{r}}\\ {b}_{{W}_{z}}\\ {b}_{{W}_{\tilde{h}}}\\ {b}_{{R}_{r}}\\ {b}_{{R}_{z}}\\ {b}_{{R}_{\tilde{h}}}\end{array}\right],$$
where the subscript R indicates that this is the bias corresponding to the recurrent weights multiplication.
The hidden state at time step t is given by
$${h}_{t}=(1{z}_{t})\odot {\tilde{h}}_{t}+{z}_{t}\odot {h}_{t1}.$$
The following formulas describe the components at time step t.
Component  ResetGateMode  Formula  

Reset gate  'aftermultiplication'  $${r}_{t}={\sigma}_{g}\left({W}_{r}{x}_{t}+{b}_{{W}_{r}}+\text{}{R}_{r}{h}_{t1}\right)$$  
'beforemultiplication'  
'recurrentbiasaftermultiplication'  $${r}_{t}={\sigma}_{g}\left({W}_{r}{x}_{t}+{b}_{{W}_{r}}+\text{}{R}_{r}{h}_{t1}+{b}_{{R}_{r}}\right)$$  
Update gate  'aftermultiplication'  $${z}_{t}={\sigma}_{g}\left({W}_{z}{x}_{t}+{b}_{{W}_{z}}+\text{}{R}_{z}{h}_{t1}\right)$$  
'beforemultiplication'  
'recurrentbiasaftermultiplication'  $${z}_{t}={\sigma}_{g}\left({W}_{z}{x}_{t}+{b}_{{W}_{z}}+\text{}{R}_{z}{h}_{t1}+{b}_{{R}_{z}}\right)$$  
Candidate state  'aftermultiplication'  $${\tilde{h}}_{t}={\sigma}_{s}\left({W}_{\tilde{h}}{x}_{t}+{b}_{{W}_{\tilde{h}}}+{r}_{t}\odot \text{}({\text{R}}_{\tilde{h}}{h}_{t1})\right)$$  
'beforemultiplication'  $${\tilde{h}}_{t}={\sigma}_{s}\left({W}_{\tilde{h}}{x}_{t}+{b}_{{W}_{\tilde{h}}}+{R}_{\tilde{h}}({r}_{t}\odot \text{}{h}_{t1})\right)$$  
'recurrentbiasaftermultiplication'  $${\tilde{h}}_{t}={\sigma}_{s}\left({W}_{\tilde{h}}{x}_{t}+{b}_{{W}_{\tilde{h}}}+{r}_{t}\odot \text{}\left({\text{R}}_{\tilde{h}}{h}_{t1}+{b}_{{R}_{\tilde{h}}}\right)\right)$$ 
In these calculations, $${\sigma}_{g}$$ and $${\sigma}_{s}$$ denotes the gate and state activation functions, respectively. The
gruLayer
function, by default, uses the sigmoid function given by $$\sigma (x)={(1+{e}^{x})}^{1}$$ to compute the gate activation function and the hyperbolic tangent
function (tanh) to compute the state activation function. To specify the state and gate
activation functions, use the StateActivationFunction
and GateActivationFunction
properties, respectively.
Layers in a layer array or layer graph pass data specified as formatted dlarray
objects.
You can interact with these dlarray
objects in automatic differentiation workflows such as when developing a custom layer, using a functionLayer
object, or using the forward
and predict
functions with dlnetwork
objects.
This table shows the supported input formats of a GRULayer
object and
the corresponding output format. If the output of the layer is passed to a custom layer that
does not inherit from the nnet.layer.Formattable
class, or a
FunctionLayer
object with the Formattable
option set
to false
, then the layer receives an unformatted dlarray
object with dimensions ordered corresponding to the formats outlined in this table.
Input Format  OutputMode  Output Format 

 "sequence" 

"last" 

In dlnetwork
objects, GRULayer
objects also support
the following input and output format combinations.
Input Format  OutputMode  Output Format 

 "sequence" 

"last" 
 
 "sequence" 

"last" 
 
 "sequence" 

"last" 

To use these input formats in trainNetwork
workflows,
first convert the data to "CBT"
(channel, batch, time) format using
flattenLayer
.
If the HasStateInputs
property is 1
(true), then
the layer has an additional input with name 'hidden'
, which corresponds
to the hidden state. This additional input expects input format "CB"
(channel, batch).
If the HasStateOutputs
property is 1
(true),
then the layer has one additional output with name 'hidden'
, which
corresponds to the hidden state. This additional output has output format
"CB"
(channel, batch).
[1] Cho, Kyunghyun, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. "Learning phrase representations using RNN encoderdecoder for statistical machine translation." arXiv preprint arXiv:1406.1078 (2014).
[2] Glorot, Xavier, and Yoshua Bengio. "Understanding the Difficulty of Training Deep Feedforward Neural Networks." In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 249–356. Sardinia, Italy: AISTATS, 2010.
[3] He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Delving Deep into Rectifiers: Surpassing HumanLevel Performance on ImageNet Classification." In Proceedings of the 2015 IEEE International Conference on Computer Vision, 1026–1034. Washington, DC: IEEE Computer Vision Society, 2015.
[4] Saxe, Andrew M., James L. McClelland, and Surya Ganguli. "Exact solutions to the nonlinear dynamics of learning in deep linear neural networks." arXiv preprint arXiv:1312.6120 (2013).
Usage notes and limitations:
The StateActivationFunction
property must be set to
'tanh'
.
The GateActivationFunction
property must be set to
'sigmoid'
.
The ResetGateMode
property must be set to
'aftermultiplication'
or
'recurrentbiasaftermultiplication'
.
The HasStateInputs
and HasStateOutputs
properties must be set to 0
(false).
Usage notes and limitations:
The StateActivationFunction
property must be set to
'tanh'
.
The GateActivationFunction
property must be set to
'sigmoid'
.
The ResetGateMode
property must be set to
'aftermultiplication'
or
'recurrentbiasaftermultiplication'
.
The HasStateInputs
and HasStateOutputs
properties must be set to 0
(false).
trainingOptions
 trainNetwork
 sequenceInputLayer
 lstmLayer
 bilstmLayer
 convolution1dLayer
 maxPooling1dLayer
 averagePooling1dLayer
 globalMaxPooling1dLayer
 globalAveragePooling1dLayer
You have a modified version of this example. Do you want to open this example with your edits?
You clicked a link that corresponds to this MATLAB command:
Run the command by entering it in the MATLAB Command Window. Web browsers do not support MATLAB commands.
Choose a web site to get translated content where available and see local events and offers. Based on your location, we recommend that you select: .
Select web siteYou can also select a web site from the following list:
Select the China site (in Chinese or English) for best site performance. Other MathWorks country sites are not optimized for visits from your location.