theanets.recurrent.Regressor

class theanets.recurrent.Regressor(layers, weighted=False, sparse_input=False)

A regressor attempts to produce a target output.

A recurrent regression model takes the following inputs:

• x: A three-dimensional array of input data. Each element of axis 0 of x is expected to be one moment in time. Each element of axis 1 of x holds a single sample from a batch of data. Each element of axis 2 of x represents the measurements of a particular input variable across all times and all data items.
• targets: A three-dimensional array of target output data. Each element of axis 0 of targets is expected to be one moment in time. Each element of axis 1 of targets holds a single sample from a batch of data. Each element of axis 2 of targets represents the measurements of a particular output variable across all times and all data items.

__init__(layers, weighted=False, sparse_input=False)

Methods

Attributes

num_params	Number of parameters in the entire network model.
params	A list of the learnable theano parameters for this network.