pydbm.synapse package

Submodules

pydbm.synapse.cnn_graph module

class pydbm.synapse.cnn_graph.CNNGraph

Bases: pydbm.synapse_list.Synapse

Computation graph in CNN.

activation_function

getter

bias_arr

getter

constant_flag

getter

deactivation_function

getter

deconvolved_bias_arr

getter

delta_deconvolved_bias_arr

getter

get_activation_function

getter

get_bias_arr

getter

get_constant_flag

getter

get_deactivation_function

getter

get_deconvolved_bias_arr

getter

get_delta_deconvolved_bias_arr

getter

get_pad

getter

get_stride

getter

get_tied_graph

getter

get_weight_arr

getter

pad

getter

set_activation_function

setter

set_bias_arr

setter

set_constant_flag

setter

set_deactivation_function

setter

set_deconvolved_bias_arr

setter

set_delta_deconvolved_bias_arr

setter

set_readonly

setter

set_tied_graph

setter

set_weight_arr

setter

stride

getter

tied_graph

getter

weight_arr

getter

pydbm.synapse.cnn_output_graph module

class pydbm.synapse.cnn_output_graph.CNNOutputGraph

Bases: pydbm.synapse_list.Synapse

Computation graph in CNN’s output layers.

activating_function

getter

bias_arr

getter

get_activating_function

getter

get_bias_arr

getter

get_weight_arr

getter

set_activating_function

setter

set_bias_arr

setter

set_weight_arr

setter

weight_arr

getter

pydbm.synapse.complete_bipartite_graph module

class pydbm.synapse.complete_bipartite_graph.CompleteBipartiteGraph

Bases: pydbm.synapse_list.Synapse

Complete Bipartite Graph.

The shallower layer is to the deeper layer what the visible layer is to the hidden layer.

create_node

Set links of nodes to the graphs.

Override.

Parameters:
  • shallower_neuron_count – The number of neurons in shallower layer.
  • deeper_neuron_count – The number of neurons in deeper layer.
  • shallower_activating_function – The activation function in shallower layer.
  • deeper_activating_function – The activation function in deeper layer.
  • weights_arr – The pre-learned weights of links. If this array is not empty, ParamsInitializer.sample_f will not be called and weights_arr will be refered as initial weights.
  • scale – Scale of parameters which will be ParamsInitializer.
  • params_initializer – is-a ParamsInitializer.
  • params_dict – dict of parameters other than size to be input to function ParamsInitializer.sample_f.
get_hidden_activating_function

getter

get_hidden_activity_arr

getter

get_hidden_bias_arr

getter

get_hidden_diff_bias_arr

getter

get_visible_activating_function

getter

get_visible_activity_arr

getter

get_visible_bias_arr

getter

get_visible_diff_bias_arr

getter

hidden_activating_function

getter

hidden_activity_arr

getter

hidden_bias_arr

getter

hidden_diff_bias_arr

getter

set_hidden_activating_function

setter

set_hidden_activity_arr

setter

set_hidden_bias_arr

setter

set_hidden_diff_bias_arr

setter

set_visible_activating_function

setter

set_visible_activity_arr

setter

set_visible_bias_arr

setter

set_visible_diff_bias_arr

setter

visible_activating_function

getter

visible_activity_arr

getter

visible_bias_arr

getter

visible_diff_bias_arr

getter

pydbm.synapse.nn_graph module

class pydbm.synapse.nn_graph.NNGraph

Bases: pydbm.synapse_list.Synapse

Computation graph in the perceptron or 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.
activation_function

getter

bias_arr

getter

get_activation_function

getter

get_bias_arr

getter

get_tied_graph

getter

get_weight_arr

getter

set_activation_function

setter

set_bias_arr

setter

set_tied_graph

setter

set_weight_arr

setter

tied_graph

getter

weight_arr

getter

pydbm.synapse.recurrent_temporal_graph module

class pydbm.synapse.recurrent_temporal_graph.RecurrentTemporalGraph

Bases: pydbm.synapse_list.Synapse

Recurrent Temporal Restricted Boltzmann Machines based on Complete Bipartite Graph.

The shallower layer is to the deeper layer what the visible layer is to the hidden layer.

create_node

Set links of nodes to the graphs.

Override.

Parameters:
  • shallower_neuron_count – The number of neurons in shallower layer.
  • deeper_neuron_count – The number of neurons in deeper layer.
  • shallower_activating_function – The activation function in shallower layer.
  • deeper_activating_function – The activation function in deeper layer.
  • weights_arr – The pre-learned weights of links. If this array is not empty, ParamsInitializer.sample_f will not be called and weights_arr will be refered as initial weights.
  • scale – Scale of parameters which will be ParamsInitializer.
  • params_initializer – is-a ParamsInitializer.
  • params_dict – dict of parameters other than size to be input to function ParamsInitializer.sample_f.
get_hat_hidden_activity_arr

getter

get_hidden_activating_function

getter

get_hidden_activity_arr

getter

get_hidden_bias_arr

getter

get_hidden_diff_bias_arr

getter

get_inferenced_arr

getter

get_pre_hidden_activity_arr

getter

get_rnn_activating_function

getter

get_rnn_hidden_bias_arr

getter

get_rnn_hidden_weights_arr

getter

get_rnn_visbile_bias_arr

getter

get_rnn_visible_weights_arr

getter

get_visible_activating_function

getter

get_visible_activity_arr

getter

get_visible_bias_arr

getter

get_visible_diff_bias_arr

getter

hat_hidden_activity_arr

getter

hidden_activating_function

getter

hidden_activity_arr

getter

hidden_bias_arr

getter

hidden_diff_bias_arr

getter

inferenced_arr

getter

pre_hidden_activity_arr

getter

rnn_activating_function

getter

rnn_hidden_bias_arr

getter

rnn_hidden_weights_arr

getter

rnn_visible_bias_arr

getter

rnn_visible_weights_arr

getter

set_hat_hidden_activity_arr

setter

set_hidden_activating_function

setter

set_hidden_activity_arr

setter

set_hidden_bias_arr

setter

set_hidden_diff_bias_arr

setter

set_inferenced_arr

setter

set_pre_hidden_activity_arr

setter

set_rnn_activating_function

setter

set_rnn_hidden_bias_arr

setter

set_rnn_hidden_weights_arr

setter

set_rnn_visible_bias_arr

setter

set_rnn_visible_weights_arr

setter

set_visible_activating_function

setter

set_visible_activity_arr

setter

set_visible_bias_arr

setter

set_visible_diff_bias_arr

setter

visible_activating_function

getter

visible_activity_arr

getter

visible_bias_arr

getter

visible_diff_bias_arr

getter

Module contents