Question

这是我为二进制图像分类编写的一个简单的MLP，带有反向传播：

class MLP:
    def __init__(self, size, epochs = 1000, learning_rate = 1):
        self.l1weights = numpy.random.random((size + 1, 3))
        self.l2weights = numpy.random.random(3)
        self.epochs = epochs
        self.learning_rate = learning_rate

    def predict(self, _input_):
        #Append bias at the beginning of input
        l1output = self.sigmoid(numpy.dot(numpy.append([1], _input_), self.l1weights))
        l2output = self.sigmoid(numpy.dot(l1output, self.l2weights))
        return l1output, l2output

    def train(self, training_set, training_goal):
        for epoch in range(self.epochs):
            l1squared_error = 0
            l2squarederror = 0
            for set_index in range(training_goal.shape[0]):
                set = training_set[set_index]
                l1output, l2output = self.predict(set)

                l2error = training_goal[set_index] - l2output
                l1error = l2error * self.dsigmoid(l2output) * self.l2weights

                self.l1weights[0] = self.l1weights[0] + self.learning_rate * l1error
                for index in range(len(self.l1weights) - 1):
                    self.l1weights[index + 1] += self.learning_rate * l1error * self.dsigmoid(l1output)
                for index in range(len(self.l2weights)):
                    self.l2weights[index] += self.learning_rate * l2error * self.dsigmoid(l2output)

                l1squared_error += sum(l1error ** 2)
                l2squarederror += l2error ** 2
            print("Squared error at epoch " + str(epoch) + " : " + str(l1squared_error) + ", " + str(l2squarederror))

    def sigmoid(self, _input_):
        #Sigmoid sigmoid function
        return 1 / (1 + numpy.exp(-_input_))

    def dsigmoid(self, _input_):
        return _input_ * (1 - _input_)

当运行时，有时所有输出收敛为1但由于某种原因，0的预测收敛为0.5，而1的预测保持在0.75附近，如果相对更成功，第2层的误差在~1000个时期后保持不变。这是使用以下代码进行2x2图像分类测试：

def image_class(input):
    return 1 if input >= 2 else 0

training_set = ((numpy.arange(2**4)[:,None] & (1 << numpy.arange(4))) != 0)
training_goals = numpy.array([image_class(sum(i)) for i in training_set])

mlp = MLP(size=4)
mlp.train(training_set, training_goals)

Answer 1

我可以通过在输出层之后添加一个步骤激活而不是sigmoid来解决这个问题，并将其与初始网络分开训练，至少是2x2识别。

多层感知器无法融合

1 个答案: