pydbm.synapse package¶
Subpackages¶
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.
getter
getter
getter
getter
-
get_visible_activating_function
¶ getter
-
get_visible_activity_arr
¶ getter
-
get_visible_bias_arr
¶ getter
-
get_visible_diff_bias_arr
¶ getter
getter
getter
getter
getter
setter
setter
setter
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.
getter
getter
getter
getter
getter
-
get_inferenced_arr
¶ getter
getter
-
get_rnn_activating_function
¶ getter
getter
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
getter
getter
getter
getter
getter
-
inferenced_arr
¶ getter
getter
-
rnn_activating_function
¶ getter
getter
getter
-
rnn_visible_bias_arr
¶ getter
-
rnn_visible_weights_arr
¶ getter
setter
setter
setter
setter
setter
-
set_inferenced_arr
¶ setter
setter
-
set_rnn_activating_function
¶ setter
setter
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
-