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 ofx
is expected to be one moment in time. Each element of axis 1 ofx
holds a single sample from a batch of data. Each element of axis 2 ofx
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 oftargets
is expected to be one moment in time. Each element of axis 1 oftargets
holds a single sample from a batch of data. Each element of axis 2 oftargets
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.