theanets.layers.feedforward.Feedforward

class theanets.layers.feedforward.Feedforward(size, inputs, name=None, activation='relu', **kwargs)

A feedforward neural network layer performs a transform of its input.

More precisely, feedforward layers as implemented here perform an affine transformation of their input, followed by a potentially nonlinear activation function performed elementwise on the transformed input.

Feedforward layers are the fundamental building block on which most neural network models are built.

Notes

This layer can be constructed using the forms 'feedforward' or 'ff'.

Parameters

  • With one input:
    • b — bias
    • w — weights
  • With \(N>1\) inputs:
    • b — bias
    • w_1 — weight for input 1
    • w_2 ...
    • w_N — weight for input \(N\)

Outputs

  • out — the post-activation state of the layer
  • pre — the pre-activation state of the layer
__init__(size, inputs, name=None, activation='relu', **kwargs)

Methods

__init__(size, inputs[, name, activation])
add_bias(name, size[, mean, std]) Helper method to create a new bias vector.
add_weights(name, nin, nout[, mean, std, ...]) Helper method to create a new weight matrix.
connect(inputs) Create Theano variables representing the outputs of this layer.
find(key) Get a shared variable for a parameter by name.
log() Log some information about this layer.
output_name([name]) Return a fully-scoped name for the given layer output.
setup() Set up the parameters and initial values for this layer.
to_spec() Create a specification dictionary 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 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, and an “out” output that gives the post-activation output.

updates : list of update pairs

An empty list of updates to apply from this layer.