Intersection Recurrent Neural Network (+RNN) cell.
Architecture with coupled recurrent gate as well as coupled depth
gate, designed to improve information flow through stacked RNNs. As the
architecture uses depth gating, the dimensionality of the depth
output (y) also should not change through depth (input size == output size).
To achieve this, the first layer of a stacked Intersection RNN projects
the inputs to N (num units) dimensions. Therefore when initializing an
IntersectionRNNCell, one should set
num_in_proj = N for the first layer
and use default settings for subsequent layers.
This implements the recurrent cell from the paper:
Jasmine Collins, Jascha Sohl-Dickstein, and David Sussillo. "Capacity and Trainability in Recurrent Neural Networks" Proc. ICLR 2017.
The Intersection RNN is built for use in deeply stacked RNNs so it may not achieve best performance with depth 1.
__init__( num_units, num_in_proj=None, initializer=None, forget_bias=1.0, y_activation=tf.nn.relu, reuse=None )
Initialize the parameters for an +RNN cell.
num_units: int, The number of units in the +RNN cell
num_in_proj: (optional) int, The input dimensionality for the RNN. If creating the first layer of an +RNN, this should be set to
num_units. Otherwise, this should be set to
None, dimensionality of
inputsshould be equal to
num_units, otherwise ValueError is thrown.
initializer: (optional) The initializer to use for the weight matrices.
forget_bias: (optional) float, default 1.0, The initial bias of the forget gates, used to reduce the scale of forgetting at the beginning of the training.
y_activation: (optional) Activation function of the states passed through depth. Default is 'tf.nn.relu`.
reuse: (optional) Python boolean describing whether to reuse variables in an existing scope. If not
True, and the existing scope already has the given variables, an error is raised.
get_initial_state( inputs=None, batch_size=None, dtype=None )
zero_state( batch_size, dtype )
Return zero-filled state tensor(s).
batch_size: int, float, or unit Tensor representing the batch size.
dtype: the data type to use for the state.
state_size is an int or TensorShape, then the return value is a
N-D tensor of shape
[batch_size, state_size] filled with zeros.
state_size is a nested list or tuple, then the return value is
a nested list or tuple (of the same structure) of
2-D tensors with
[batch_size, s] for each s in