theanets.layers.recurrent.LRRNN¶
-
class
theanets.layers.recurrent.
LRRNN
(size, inputs, name=None, activation='relu', **kwargs)¶ An RNN with learned rate for each unit.
Notes
In a normal RNN, a hidden unit is updated completely at each time step, \(h_t = f(x_t, h_{t-1})\). With an explicit update rate, the state of a hidden unit is computed as a mixture of the new and old values,
\[h_t = (1 - z_t) \odot h_{t-1} + z_t \odot f(x_t, h_{t-1})\]where \(\odot\) indicates elementwise multiplication.
Rates might be defined in a number of ways, spanning a continuum between vanilla RNNs (i.e., all rate parameters are fixed at 1), fixed but non-uniform rates for each hidden unit [Ben12], parametric rates that are dependent only on the input (i.e., the
ARRNN
), all the way to parametric rates that are computed as a function of the inputs and the hidden state at each time step (i.e., something more like thegated recurrent unit
).This class represents rates as a single learnable vector of parameters. This representation uses the fewest number of parameters for learnable rates, but the simplicity of the model comes at the cost of effectively fixing the rate for each unit as a constant value across time.
Parameters
b
— vector of bias values for each hidden unitr
— vector of rates for each hidden unitxh
— matrix connecting inputs to hidden unitshh
— matrix connecting hiddens to hiddens
Outputs
out
— the post-activation state of the layerpre
— the pre-activation state of the layerhid
— the pre-rate-mixing hidden staterate
— the rate values
References
[Ben12] (1, 2) Y. Bengio, N. Boulanger-Lewandowski, & R. Pascanu. (2012) “Advances in Optimizing Recurrent Networks.” http://arxiv.org/abs/1212.0901 -
__init__
(size, inputs, name=None, activation='relu', **kwargs)¶
Methods
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
()Set up the parameters and initial values for this layer. transform
(inputs)Transform the inputs for this layer into an output 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. -
setup
()¶ Set up the parameters and initial values for this layer.
-
transform
(inputs)¶ Transform the inputs for this layer into an output 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 : theano expression
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 rate-independent, post-activation hidden state, a “rate” output that gives the rate value for each hidden unit, and an “out” output that gives the hidden output.
updates : list of update pairs
A sequence of updates to apply inside a theano function.