为什么我的XOR神经网络收敛到0.5,python
我已经实现了以下神经网络来解决Python中的XOR问题。我的神经网络由2个神经元的输入层、2个神经元的1个隐藏层和1个神经元的输出层组成。我正在使用Sigmoid函数作为隐藏层和输出层的激活函数。有人能解释一下我做错了什么吗为什么我的XOR神经网络收敛到0.5,python,python,neural-network,Python,Neural Network,我已经实现了以下神经网络来解决Python中的XOR问题。我的神经网络由2个神经元的输入层、2个神经元的1个隐藏层和1个神经元的输出层组成。我正在使用Sigmoid函数作为隐藏层和输出层的激活函数。有人能解释一下我做错了什么吗 import numpy import scipy.special class NeuralNetwork: def __init__(self, inputNodes, hiddenNodes, outputNodes, learningRate):
import numpy
import scipy.special
class NeuralNetwork:
def __init__(self, inputNodes, hiddenNodes, outputNodes, learningRate):
self.iNodes = inputNodes
self.hNodes = hiddenNodes
self.oNodes = outputNodes
self.wIH = numpy.random.normal(0.0, pow(self.iNodes, -0.5), (self.hNodes, self.iNodes))
self.wOH = numpy.random.normal(0.0, pow(self.hNodes, -0.5), (self.oNodes, self.hNodes))
self.lr = learningRate
self.activationFunction = lambda x: scipy.special.expit(x)
def train(self, inputList, targetList):
inputs = numpy.array(inputList, ndmin=2).T
targets = numpy.array(targetList, ndmin=2).T
#print(inputs, targets)
hiddenInputs = numpy.dot(self.wIH, inputs)
hiddenOutputs = self.activationFunction(hiddenInputs)
finalInputs = numpy.dot(self.wOH, hiddenOutputs)
finalOutputs = self.activationFunction(finalInputs)
outputErrors = targets - finalOutputs
hiddenErrors = numpy.dot(self.wOH.T, outputErrors)
self.wOH += self.lr * numpy.dot((outputErrors * finalOutputs * (1.0 - finalOutputs)), numpy.transpose(hiddenOutputs))
self.wIH += self.lr * numpy.dot((hiddenErrors * hiddenOutputs * (1.0 - hiddenOutputs)), numpy.transpose(inputs))
def query(self, inputList):
inputs = numpy.array(inputList, ndmin=2).T
hiddenInputs = numpy.dot(self.wIH, inputs)
hiddenOutputs = self.activationFunction(hiddenInputs)
finalInputs = numpy.dot(self.wOH, hiddenOutputs)
finalOutputs = self.activationFunction(finalInputs)
return finalOutputs
nn = NeuralNetwork(2, 2, 1, 0.01)
data = [[0, 0, 0], [0, 1, 1], [1, 0, 1], [1, 1, 0]]
epochs = 10
for e in range(epochs):
for record in data:
inputs = numpy.asfarray(record[1:])
targets = record[0]
#print(targets)
#print(inputs, targets)
nn.train(inputs, targets)
print(nn.query([0, 0]))
print(nn.query([1, 0]))
print(nn.query([0, 1]))
print(nn.query([1, 1]))
有几个原因
# transfer functions
def sigmoid(x):
return 1 / (1 + np.exp(-x))
# derivative of sigmoid
def dsigmoid(y):
return y * (1.0 - y)
# using tanh over logistic sigmoid for the hidden layer is recommended
def tanh(x):
return np.tanh(x)
# derivative for tanh sigmoid
def dtanh(y):
return 1 - y*y