我正在研究一些神经网络代码。我已经编写了自己的神经元课程，可以找到here。现在，我正在编写脑类，这应该会使NN中使用的大多数代码变得非常有用。在这个类中，self.Real_Outputs收集所有输出并将其放入要在之后使用的列表中。
我正在沸腾我的大脑以找出为什么当我在self中添加元素时.Real_Outputs整个列表都会收到此值。我发现here in this topic类似于我的讨论，但是，在我的情况下，我已经使用过＆＃39; self＆＃39;声明。你能帮助我吗？
班级大脑：
def __init__(self, training_set, desired_outputs, bias, learning_tax):
self.Training_Set = training_set
self.Desired_Outputs = desired_outputs
self.Bias = bias
self.Learning_Tax = learning_tax
self.Hidden_Layer = []
self.Hidden_Layer_Outputs = []
self.Hidden_Layer_Errors = []
self.Output_Layer = []
self.Output_Layer_Outputs = []
self.Output_Layer_Errors = []
self.Real_Outputs = [0 for x in self.Desired_Outputs]
def set_hidden_layers(self, number_of_layers, number_of_neurons, activation_function):
self.Hidden_Layer = [[Neuron.Neuron(len(self.Training_Set[0]), activation_function, 1, self.Bias)
for x in range(number_of_neurons)]
for y in range(number_of_layers)]
self.Hidden_Layer_Outputs = [[0 for x in range(number_of_neurons)]
for y in range(number_of_layers)]
self.Hidden_Layer_Errors = [[0 for x in range(number_of_neurons)]
for y in range(number_of_layers)]
def set_output_layer(self, number_of_neurons, activation_function):
self.Output_Layer = [Neuron.Neuron(len(self.Hidden_Layer[0]), activation_function, 0, self.Bias)
for x in range(number_of_neurons)]
self.Output_Layer_Outputs = [0 for x in range(number_of_neurons)]
self.Output_Layer_Errors = [0 for x in range(number_of_neurons)]
def start_converging(self):
j=0
while j < 10:
# Here we're coming inside the training set. If was the n-th time
# you pass here, it's the n-th iteration over the Training Set.
# 'a' represents the Training Set index
for a in range(len(self.Training_Set)):
# Here we're running over the hidden layers
# 'b' represent the layer index
for b in range(len(self.Hidden_Layer)):
# Here we're running over the neurons in the layers
# 'c' represents the neuron index
for c in range(len(self.Hidden_Layer[b])):
if b == 0:
self.Hidden_Layer[b][c].initialize_inputs(self.Training_Set[a])
self.Hidden_Layer[b][c].get_sum()
self.Hidden_Layer_Outputs[b][c] = self.Hidden_Layer[b][c].get_output()
else:
self.Hidden_Layer[b][c].initialize_inputs(self.Hidden_Layer_Outputs[b-1])
self.Hidden_Layer[b][c].get_sum()
self.Hidden_Layer_Outputs[b][c] = self.Hidden_Layer[b][c].get_output()
# Here we're running over the output layer
# 'd' represents the neuron index
for d in range(len(self.Output_Layer)):
self.Output_Layer[d].initialize_inputs(self.Hidden_Layer_Outputs[-1])
self.Output_Layer[d].get_sum()
self.Output_Layer_Outputs[d] = self.Output_Layer[d].get_output()
self.Output_Layer_Errors[d] = self.Output_Layer[d].get_error(0, self.Desired_Outputs[a])
self.Output_Layer[d].update_weights(0, self.Learning_Tax)
self.Real_Outputs[a] = self.Output_Layer_Outputs
# We're updating the hidden layers now. Notice that we should pass backwards, from
# last to first, so, we're using [-(e+1)] indexes.
# '[-(e+1)]' represents the layers index.
for e in range(len(self.Hidden_Layer)):
for f in range(len(self.Hidden_Layer[-(e+1)])):
if e == 0:
self.Hidden_Layer_Errors[-(e + 1)][-(f + 1)] = self.Hidden_Layer[-(e + 1)][-(f + 1)].get_error(0, self.Output_Layer_Errors)
self.Hidden_Layer[-(e + 1)][-(f + 1)].update_weights(0, self.Learning_Tax)
else:
self.Hidden_Layer[-(e + 1)][-(f + 1)].get_error(0, self.Hidden_Layer_Errors[- (e + 1)])
self.Hidden_Layer[-(e + 1)][-(f + 1)].update_weights(0, self.Learning_Tax)
j += 1
print (self.Desired_Outputs)
print (self.Real_Outputs)