CloneSet123


Previous CloneSetNext CloneSetBack to Main Report
Clone
Mass
Clones in
CloneSet
Parameter
Count
Clone
Similarity
Syntax Category
[Sequence Length]
17201.000stmt_list[2]
Clone AbstractionParameter Bindings
Clone Instance
(Click to see clone)
Line CountSource Line
Source File
116127
Bio/NeuralNetwork/BackPropagation/Layer.py
217219
Bio/NeuralNetwork/BackPropagation/Layer.py
Clone Instance
1
Line Count
16
Source Line
127
Source File
Bio/NeuralNetwork/BackPropagation/Layer.py

        # first backpropogate to the next layers
        next_errors = self._next_layer.backpropagate(outputs,learning_rate,momentum) 


        for this_node in self.nodes: 
             for next_node in self._next_layer.nodes: 
                  error_deriv = (next_errors[next_node]*self.values[this_node]) 


                  delta = (learning_rate*error_deriv+momentum*self.weight_changes[(this_node,next_node)]) 


                  # apply the change to the weight
                  self.weights[(this_node,next_node)]+=delta 

                  # remember the weight change for next time
                  self.weight_changes[(this_node,next_node)] =  delta 
             


Clone Instance
2
Line Count
17
Source Line
219
Source File
Bio/NeuralNetwork/BackPropagation/Layer.py

        # first backpropogate to the next layers
        next_errors = self._next_layer.backpropagate(outputs,learning_rate,momentum) 


        # --- update the weights
        for this_node in self.nodes: 
             for next_node in self._next_layer.nodes: 
                  error_deriv = (next_errors[next_node]*self.values[this_node]) 


                  delta = (learning_rate*error_deriv+momentum*self.weight_changes[(this_node,next_node)]) 


                  # apply the change to the weight
                  self.weights[(this_node,next_node)]+=delta 

                  # remember the weight change for next time
                  self.weight_changes[(this_node,next_node)] =  delta 

          # --- calculate error terms
             


Clone AbstractionParameter Count: 0Parameter Bindings

# first backpropogate to the next layers
next_errors = self._next_layer.backpropagate(outputs,learning_rate,momentum) 
# --- update the weights
for this_node in self.nodes:
  for next_node in self._next_layer.nodes:
  
    error_deriv = (next_errors[next_node]*self.values[this_node]) 
    delta = (learning_rate*error_deriv+momentum*self.weight_changes[(this_node,next_node)]) 
    # apply the change to the weight
    self.weights[(this_node,next_node)]+=delta 
    # remember the weight change for next time
    self.weight_changes[(this_node,next_node)] = delta 
    # --- calculate error terms
  
 

CloneAbstraction
Parameter Bindings
Parameter
Index
Clone
Instance
Parameter
Name
Value
None