pydbm.rnn.interface package

Submodules

pydbm.rnn.interface.reconstructable_model module

class pydbm.rnn.interface.reconstructable_model.ReconstructableModel

Bases: object

The interface of reconstructable model.

get_feature_points

Extract feature points.

Returns:Array like or sparse matrix of feature points.
hidden_back_propagate

Back propagation in hidden layer.

Parameters:delta_output_arr – Delta.
Returns:Tuple data. - np.ndarray of Delta, - list of gradations.
inference

Inference the feature points to reconstruct the time-series.

Parameters:
  • observed_arr – Array like or sparse matrix as the observed data points.
  • hidden_activity_arr – Array like or sparse matrix as the state in hidden layer.
  • cec_activity_arr – Array like or sparse matrix as the state in RNN.
Returns:

Tuple data. - Array like or sparse matrix of reconstructed instances of time-series, - Array like or sparse matrix of the state in hidden layer, - Array like or sparse matrix of the state in RNN.
learn

Learn the observed data points for vector representation of the input time-series.

Override.

Parameters:
  • observed_arr – Array like or sparse matrix as the observed data points.
  • target_arr – Array like or sparse matrix as the target data points. To learn as Auto-encoder, this value must be None or equivalent to observed_arr.
load_pre_learned_params

Load pre-learned parameters.

Parameters:
  • dir_name – Path of dir. If None, the file is saved in the current directory.
  • file_name – File name.
opt_params

is-a OptParams

save_pre_learned_params

Save pre-learned parameters.

Parameters:
  • dir_name – Path of dir. If None, the file is saved in the current directory.
  • file_name – File name.

Module contents