我有一个我在python中工作的神经网络模型 . 然而，反向传播似乎不起作用，而且我已经摆弄了一段时间 . 通过一系列培训，即使有足够的数据，输出也将平均为0.5 . 这是反向传播的代码和数据，只是一个简单的AND门输出：数据：
data = [[[1, 1], 1],
[[1, 0], 0],
[[0, 1], 0],
[[0, 0], 0]]
backprop：
def backpropagate(self, input, output, learning_rate=0.2):
expected = self.feed_forward(input) # expected output
state = self.feed_full(input)
error = output - expected # error
delta = error * self.activation_function(expected, True)
for weight_layer in reversed(range(len(self.weights))):
error = delta.dot(self.weights[weight_layer].T) # updating error
delta = error * self.activation_function(state[weight_layer], True) # updating delta for each layer
self.weights[weight_layer] += np.transpose(state[weight_layer]).dot(delta) * learning_rate
为所有州提供食物并输出：
def feed_forward(self, x):
ret = x
for weight_layer in self.weights:
ret = self.activation_function(np.dot(ret, weight_layer))
return ret
def feed_full(self, x):
state = x
activations = [x]
for weight_layer in self.weights:
state = self.activation_function(np.dot(state, weight_layer))
activations.append(state)
return activations
网的形状是[2,3,1]，我正在尝试设计它，以便形状可扩展，所以我可以将它用于其他项目 . 只需要backprop部分 . 谢谢 .