theanets.recurrent.Autoencoder

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

An autoencoder network attempts to reproduce its input.

A recurrent autoencoder model requires the following inputs during training:

• 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 represents a single data sample in a batch of samples. Each element of axis 2 of x represents the measurements of a particular input 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.
tied_weights	A boolean indicating whether this network uses tied weights.