pydbm.nn package

Submodules

pydbm.nn.neural_network module

class pydbm.nn.neural_network.NeuralNetwork

Bases: object

Neural Network.

References

  • Kamyshanska, H., & Memisevic, R. (2014). The potential energy of an autoencoder. IEEE transactions on pattern analysis and machine intelligence, 37(6), 1261-1273.
back_propagation

Back propagation in NN.

Parameters:Delta. –
Returns.
Delta.
computable_loss

getter

forward_propagation

Forward propagation in NN.

Parameters:observed_arr – np.ndarray of image file array.
Returns:Propagated np.ndarray.
get_computable_loss

getter

get_nn_layer_list

getter

get_opt_params

getter

get_verificatable_result

getter

get_weight_decay_term

getter

inference

Inference the feature points to reconstruct the time-series.

Override.

Parameters:observed_arr – Array like or sparse matrix as the observed data points.
Returns:Predicted array like or sparse matrix.
learn

Learn.

Parameters:
  • observed_arr – np.ndarray of observed data points.
  • target_arr – np.ndarray of labeled data. If None, the function of this NN model is equivalent to Convolutional Auto-Encoder.
nn_layer_list

getter

opt_params

getter

optimize

Back propagation.

Parameters:
  • learning_rate – Learning rate.
  • epoch – Now epoch.
save_pre_learned_params

Save pre-learned parameters.

Parameters:
  • dir_path – Path of dir. If None, the file is saved in the current directory.
  • file_name – The naming rule of files. If None, this value is nn.
set_computable_loss

setter

set_nn_layer_list

setter

set_opt_params

setter

set_verificatable_result

setter

set_weight_decay_term

setter

verificatable_result

getter

weight_decay_term

getter

pydbm.nn.nn_layer module

class pydbm.nn.nn_layer.NNLayer

Bases: object

NN Layer.

back_propagate

Back propagation in CNN layers.

Override.

Parameters:delta_arr – 2-rank array like or sparse matrix.
Returns:2-rank array like or sparse matrix.
delta_bias_arr

getter

delta_weight_arr

getter

forward_propagate

Forward propagation in NN layers.

Override.

Parameters:observed_arr – 2-rank array like or sparse matrix.
Returns:4-rank array like or sparse matrix.
get_delta_bias_arr

getter

get_delta_weight_arr

getter

get_graph

getter

graph

getter

reset_delta

Reset delta.

set_delta_bias_arr

setter

set_delta_weight_arr

setter

set_readonly

setter

pydbm.nn.simple_auto_encoder module

class pydbm.nn.simple_auto_encoder.SimpleAutoEncoder

Bases: object

Auto-Encoder.

References

  • Kamyshanska, H., & Memisevic, R. (2014). The potential energy of an autoencoder. IEEE transactions on pattern analysis and machine intelligence, 37(6), 1261-1273.
back_propagation

Back propagation in NN.

Parameters:Delta. –
Returns.
Delta.
computable_loss

getter

decoder

getter

encoder

getter

forward_propagation

Forward propagation in NN.

Parameters:observed_arr – np.ndarray of image file array.
Returns:Propagated np.ndarray.
get_computable_loss

getter

get_decoder

getter

get_encoder

getter

get_verificatable_result

getter

inference

Inference the feature points to reconstruct the time-series.

Override.

Parameters:observed_arr – Array like or sparse matrix as the observed data points.
Returns:Predicted array like or sparse matrix.
learn

Learn.

Parameters:
  • observed_arr – np.ndarray of observed data points.
  • target_arr – np.ndarray of labeled data. If None, the function of this NN model is equivalent to Convolutional Auto-Encoder.
optimize

Back propagation.

Parameters:
  • learning_rate – Learning rate.
  • epoch – Now epoch.
set_computable_loss

setter

set_decoder

setter

set_encoder

setter

set_verificatable_result

setter

verificatable_result

getter

Module contents