theanets.layers.recurrent.GRU

class theanets.layers.recurrent.GRU(**kwargs)

Gated Recurrent Unit layer.

The implementation is from J Chung, C Gulcehre, KH Cho, & Y Bengio (2014), “Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling” (page 4), available at http://arxiv.org/abs/1412.3555v1.

__init__(**kwargs)

Methods

__init__(**kwargs)
add_weights(name, nin, nout[, mean, std, ...])	Helper method to create a new weight matrix.
initial_state(name, batch_size)	Return an array of suitable for representing initial state.
setup()
transform(inputs)	Transform inputs to this layer into outputs for the layer.

Attributes

input_size	For networks with one input, get the input size.
num_params	Total number of learnable parameters in this layer.
params	A list of all parameters in this layer.

transform(inputs)

Transform inputs to this layer into outputs for the layer.

Parameters:

inputs : dict of theano expressions

Symbolic inputs to this layer, given as a dictionary mapping string names to Theano expressions. See base.Layer.connect().

Returns:

outputs : dict of theano expressions

A map from string output names to Theano expressions for the outputs from this layer. This layer type generates a “pre” output that gives the unit activity before applying the layer’s activation function, a “hid” output that gives the post-activation values before applying the rate mixing, and an “out” output that gives the overall output.

updates : sequence of update pairs

A sequence of updates to apply to this layer’s state inside a theano function.