神经网络反向传播BackPropagation

尤里西斯
168 阅读3分钟

三层神经网络

image.png

输入层

{x1, x2, x3, ..., x4} 参数向量, 对应神经元的激活或者静息

隐藏层

特征提取，信息变换的过程，将输入的参数向量，转换成期望的结果。每一个节点会对输入层的兴奋有不同的接收权重

输出层

输出结果{o1, o2}

  • 自编码模型（Auto-Encoder）: 输入输出节点个数一样，目的降维、去噪
  • 二分类模型：结果集{o1, o2}，如果o1节点兴奋度比o2更高，则结果倾向于o1

信息传递

输入层神经元对应原始数据，基于不通过的权重向隐藏层提供信息，形成特定的模式，激活对应的神经元，隐藏层的神经元激活后，继续前向传播信息，同时也加上不同的激活权重，输出层最终的兴奋度就是模型的结果

输入层到隐藏层

outh1=Sigmoid(w1∗x1+w2∗x2+w3∗x3+b)out_{h1} = Sigmoid( w_1 * x_1 + w_2 * x_2 + w_3 * x_3 + b)

权重影响神经元对不同输入信息敏感程度

偏置影响神经元对信息的敏感度，有过滤信息中噪音的作用

激活函数 ： Tanh(x)=21+e−2x−1Tanh(x) = \frac{2}{1 + e^{-2x}} - 1 （引入非线性，使线性组合的结果经过激活函数后逼近非线性函数）

隐藏层到输出层

node(o1)=w1∗outh1+w2∗outh2+w3∗outh3+bnode(o1) = w_1 * out_{h1} + w_2 * out_{h2} + w_3 * out_{h3} + b 激活函数 ： Sigmoid(x)=11+e−xSigmoid(x) = \frac{1}{1 + e^{-x}} （引入非线性，使线性组合的结果经过激活函数后逼近非线性函数）

损失函数

衡量模型好坏的标准，表现预测值与实际值之间的差距

分类问题经典损失函数： Softmax(zi)=ezi∑c=1CezcSoftmax(z_i) = \frac{e^{z_i}}{\sum_{c=1}^{C}}e^{z_c}

梯度下降

梯度，函数偏导数，梯度下降的过程就是求解函数最值的问题，模型优化的过程，也就是求解损失函数最小值的问题

反向传播

image.png

l = Loss(y^,y)=∑i=1n(yi−y^i)2Loss(ŷ, y) = \sum_{i=1}^{n}(y^i - ŷ^i) ^2

反向传播评估权重对最终误差的影响，对w求导

θlθw=θlθzθzθw\frac{\theta l}{\theta w} = \frac{\theta l}{\theta z}\frac{\theta z}{\theta w}

θzθw1=x1\frac{\theta z}{\theta w_1} = x_1, θzθw2=x2\frac{\theta z}{\theta w_2} = x_2 (公式0)

θlθz=θaθzθlθa=σ′(z)θlθa\frac{\theta l}{\theta z} = \frac{\theta a}{\theta z}\frac{\theta l}{\theta a} = \sigma^{\prime}(z)\frac{\theta l}{\theta a} (公式1)

代码


#coding:utf-8
import random
import math

#
#   参数解释：
#   "pd_" ：偏导的前缀
#   "d_" ：导数的前缀
#   "w_ho" ：隐含层到输出层的权重系数索引
#   "w_ih" ：输入层到隐含层的权重系数的索引

class NeuralNetwork:
    LEARNING_RATE = 0.5

    def __init__(self, num_inputs, num_hidden, num_outputs, hidden_layer_weights = None, hidden_layer_bias = None, output_layer_weights = None, output_layer_bias = None):
        self.num_inputs = num_inputs

        self.hidden_layer = NeuronLayer(num_hidden, hidden_layer_bias)
        self.output_layer = NeuronLayer(num_outputs, output_layer_bias)

        self.init_weights_from_inputs_to_hidden_layer_neurons(hidden_layer_weights)
        self.init_weights_from_hidden_layer_neurons_to_output_layer_neurons(output_layer_weights)

    def init_weights_from_inputs_to_hidden_layer_neurons(self, hidden_layer_weights):
        weight_num = 0
        for h in range(len(self.hidden_layer.neurons)):
            for i in range(self.num_inputs):
                if not hidden_layer_weights:
                    self.hidden_layer.neurons[h].weights.append(random.random())
                else:
                    self.hidden_layer.neurons[h].weights.append(hidden_layer_weights[weight_num])
                weight_num += 1

    def init_weights_from_hidden_layer_neurons_to_output_layer_neurons(self, output_layer_weights):
        weight_num = 0
        for o in range(len(self.output_layer.neurons)):
            for h in range(len(self.hidden_layer.neurons)):
                if not output_layer_weights:
                    self.output_layer.neurons[o].weights.append(random.random())
                else:
                    self.output_layer.neurons[o].weights.append(output_layer_weights[weight_num])
                weight_num += 1

    def inspect(self):
        print('------')
        print('* Inputs: {}'.format(self.num_inputs))
        print('------')
        print('Hidden Layer')
        self.hidden_layer.inspect()
        print('------')
        print('* Output Layer')
        self.output_layer.inspect()
        print('------')

    def feed_forward(self, inputs):
        hidden_layer_outputs = self.hidden_layer.feed_forward(inputs)
        return self.output_layer.feed_forward(hidden_layer_outputs)

    def train(self, training_inputs, training_outputs):
        self.feed_forward(training_inputs)

        # 1. 输出神经元的值
        pd_errors_wrt_output_neuron_total_net_input = [0] * len(self.output_layer.neurons)
        for o in range(len(self.output_layer.neurons)):

            # ∂E/∂zⱼ
            pd_errors_wrt_output_neuron_total_net_input[o] = self.output_layer.neurons[o].calculate_pd_error_wrt_total_net_input(training_outputs[o])

        # 2. 隐含层神经元的值
        pd_errors_wrt_hidden_neuron_total_net_input = [0] * len(self.hidden_layer.neurons)
        for h in range(len(self.hidden_layer.neurons)):

            # dE/dyⱼ = Σ ∂E/∂zⱼ * ∂z/∂yⱼ = Σ ∂E/∂zⱼ * wᵢⱼ
            d_error_wrt_hidden_neuron_output = 0
            for o in range(len(self.output_layer.neurons)):
                d_error_wrt_hidden_neuron_output += pd_errors_wrt_output_neuron_total_net_input[o] * self.output_layer.neurons[o].weights[h]

            # ∂E/∂zⱼ = dE/dyⱼ * ∂zⱼ/∂
            pd_errors_wrt_hidden_neuron_total_net_input[h] = d_error_wrt_hidden_neuron_output * self.hidden_layer.neurons[h].calculate_pd_total_net_input_wrt_input()

        # 3. 更新输出层权重系数
        for o in range(len(self.output_layer.neurons)):
            for w_ho in range(len(self.output_layer.neurons[o].weights)):

                # ∂Eⱼ/∂wᵢⱼ = ∂E/∂zⱼ * ∂zⱼ/∂wᵢⱼ
                pd_error_wrt_weight = pd_errors_wrt_output_neuron_total_net_input[o] * self.output_layer.neurons[o].calculate_pd_total_net_input_wrt_weight(w_ho)

                # Δw = α * ∂Eⱼ/∂wᵢ
                self.output_layer.neurons[o].weights[w_ho] -= self.LEARNING_RATE * pd_error_wrt_weight

        # 4. 更新隐含层的权重系数
        for h in range(len(self.hidden_layer.neurons)):
            for w_ih in range(len(self.hidden_layer.neurons[h].weights)):

                # ∂Eⱼ/∂wᵢ = ∂E/∂zⱼ * ∂zⱼ/∂wᵢ
                pd_error_wrt_weight = pd_errors_wrt_hidden_neuron_total_net_input[h] * self.hidden_layer.neurons[h].calculate_pd_total_net_input_wrt_weight(w_ih)

                # Δw = α * ∂Eⱼ/∂wᵢ
                self.hidden_layer.neurons[h].weights[w_ih] -= self.LEARNING_RATE * pd_error_wrt_weight

    def calculate_total_error(self, training_sets):
        total_error = 0
        for t in range(len(training_sets)):
            training_inputs, training_outputs = training_sets[t]
            self.feed_forward(training_inputs)
            for o in range(len(training_outputs)):
                total_error += self.output_layer.neurons[o].calculate_error(training_outputs[o])
        return total_error

class NeuronLayer:
    def __init__(self, num_neurons, bias):

        # 同一层的神经元共享一个截距项b
        self.bias = bias if bias else random.random()

        self.neurons = []
        for i in range(num_neurons):
            self.neurons.append(Neuron(self.bias))

    def inspect(self):
        print('Neurons:', len(self.neurons))
        for n in range(len(self.neurons)):
            print(' Neuron', n)
            for w in range(len(self.neurons[n].weights)):
                print('  Weight:', self.neurons[n].weights[w])
            print('  Bias:', self.bias)

    def feed_forward(self, inputs):
        outputs = []
        for neuron in self.neurons:
            outputs.append(neuron.calculate_output(inputs))
        return outputs

    def get_outputs(self):
        outputs = []
        for neuron in self.neurons:
            outputs.append(neuron.output)
        return outputs

class Neuron:
    def __init__(self, bias):
        self.bias = bias
        self.weights = []

    def calculate_output(self, inputs):
        self.inputs = inputs
        self.output = self.squash(self.calculate_total_net_input())
        return self.output

    def calculate_total_net_input(self):
        total = 0
        for i in range(len(self.inputs)):
            total += self.inputs[i] * self.weights[i]
        return total + self.bias

    # 激活函数sigmoid
    def squash(self, total_net_input):
        return 1 / (1 + math.exp(-total_net_input))


    def calculate_pd_error_wrt_total_net_input(self, target_output):
        return self.calculate_pd_error_wrt_output(target_output) * self.calculate_pd_total_net_input_wrt_input();

    # 每一个神经元的误差是由平方差公式计算的
    def calculate_error(self, target_output):
        return 0.5 * (target_output - self.output) ** 2


    def calculate_pd_error_wrt_output(self, target_output):
        return -(target_output - self.output)


    def calculate_pd_total_net_input_wrt_input(self):
        return self.output * (1 - self.output)


    def calculate_pd_total_net_input_wrt_weight(self, index):
        return self.inputs[index]


# 文中的例子:

nn = NeuralNetwork(2, 2, 2, hidden_layer_weights=[0.15, 0.2, 0.25, 0.3], hidden_layer_bias=0.35, output_layer_weights=[0.4, 0.45, 0.5, 0.55], output_layer_bias=0.6)
for i in range(10000):
    nn.train([0.05, 0.1], [0.01, 0.09])
    print(i, round(nn.calculate_total_error([[[0.05, 0.1], [0.01, 0.09]]]), 9))


#另外一个例子，可以把上面的例子注释掉再运行一下:

# training_sets = [
#     [[0, 0], [0]],
#     [[0, 1], [1]],
#     [[1, 0], [1]],
#     [[1, 1], [0]]
# ]

# nn = NeuralNetwork(len(training_sets[0][0]), 5, len(training_sets[0][1]))
# for i in range(10000):
#     training_inputs, training_outputs = random.choice(training_sets)
#     nn.train(training_inputs, training_outputs)
#     print(i, nn.calculate_total_error(training_sets))
avatar
文章
阅读
粉丝