| Previous CloneSet | Next CloneSet | Back to Main Report |
| Clone Mass | Clones in CloneSet | Parameter Count | Clone Similarity | Syntax Category [Sequence Length] |
|---|---|---|---|---|
| 20 | 2 | 1 | 0.998 | stmt_list[6] |
| Clone Abstraction | Parameter Bindings |
| Clone Instance (Click to see clone) | Line Count | Source Line | Source File |
|---|---|---|---|
| 1 | 21 | 74 | Bio/NeuralNetwork/BackPropagation/Layer.py |
| 2 | 20 | 164 | Bio/NeuralNetwork/BackPropagation/Layer.py |
| ||||
# set up the weights
self.weights = { }
for own_node in self.nodes:
for other_node in self._next_layer.nodes:
self.weights[(own_node,other_node)] =
random.randrange( -2.0,2.0)
# set up the weight changes
self.weight_changes = { }
for own_node in self.nodes:
for other_node in self._next_layer.nodes:
self.weight_changes[(own_node,other_node)] = 0.0
# set up the calculated values for each node -- these will
# actually just be set from inputs into the network.
self.values = { }
for node in self.nodes:
# set the bias node -- always has a value of 1
if node==0:
self.values[0] = 1
else:
self.values[node] = 0
|
| ||||
# set up the weights
self.weights = { }
for own_node in self.nodes:
for other_node in self._next_layer.nodes:
self.weights[(own_node,other_node)] =
random.randrange( -2.0,2.0)
# set up the weight changes
self.weight_changes = { }
for own_node in self.nodes:
for other_node in self._next_layer.nodes:
self.weight_changes[(own_node,other_node)] = 0.0
# set up the calculated values for each node
self.values = { }
for node in self.nodes:
# bias node
if node==0:
self.values[node] = 1
else:
self.values[node] = 0
|
| |||
# set up the weights
self.weights = { }
for own_node in self.nodes:
for other_node in self._next_layer.nodes:
self.weights[(own_node,other_node)] = random.randrange( -2.0,2.0)
# set up the weight changes
self.weight_changes = { }
for own_node in self.nodes:
for other_node in self._next_layer.nodes:
self.weight_changes[(own_node,other_node)] = 0.0
# set up the calculated values for each node
# set up the calculated values for each node -- these will
# actually just be set from inputs into the network.
self.values = { }
for node in self.nodes:
# bias node
# set the bias node -- always has a value of 1
if node==0:
self.values[ [[#variable78abc4c0]]] = 1
else:
self.values[node] = 0
|
| CloneAbstraction |
| Parameter Index | Clone Instance | Parameter Name | Value |
|---|---|---|---|
| 1 | 1 | [[#78abc4c0]] | node |
| 1 | 2 | [[#78abc4c0]] | 0 |