| Previous CloneSet | Next CloneSet | Back to Main Report |
| Clone Mass | Clones in CloneSet | Parameter Count | Clone Similarity | Syntax Category [Sequence Length] |
|---|---|---|---|---|
| 8 | 2 | 2 | 0.950 | compound_stmt |
| Clone Abstraction | Parameter Bindings |
| Clone Instance (Click to see clone) | Line Count | Source Line | Source File |
|---|---|---|---|
| 1 | 8 | 193 | Bio/NeuralNetwork/BackPropagation/Layer.py |
| 2 | 8 | 283 | Bio/NeuralNetwork/BackPropagation/Layer.py |
| ||||
# update each node in this network
for update_node in self.nodes[1: ]:
# sum up the weighted inputs from the previous network
sum = 0.0
for node in previous_layer.nodes:
sum+=(previous_layer.values[node]*previous_layer.weights[(node,update_node)])
self.values[update_node] = self._activation(sum)
# propogate the update to the next layer
|
| ||||
# update all of the nodes in this layer
for update_node in self.nodes:
# sum up the contribution from all of the previous inputs
sum = 0.0
for node in previous_layer.nodes:
sum+=(previous_layer.values[node]*previous_layer.weights[(node,update_node)])
self.values[update_node] = self._activation(sum)
|
| |||
# update all of the nodes in this layer
# update each node in this network
for update_node in [[#variable5d6e11a0]] [[#variable5d6e12c0]]:
# sum up the contribution from all of the previous inputs
# sum up the weighted inputs from the previous network
sum = 0.0
for node in previous_layer.nodes:
sum+=(previous_layer.values[node]*previous_layer.weights[(node,update_node)])
self.values[update_node] = self._activation(sum)
# propogate the update to the next layer
|
| CloneAbstraction |
| Parameter Index | Clone Instance | Parameter Name | Value |
|---|---|---|---|
| 1 | 1 | [[#5d6e11a0]] | self |
| 1 | 2 | [[#5d6e11a0]] | self.nodes |
| 2 | 1 | [[#5d6e12c0]] | .nodes |
| 2 | 2 | [[#5d6e12c0]] | [1: ] |