本文完全利用numpy实现一个简单的BP神经网络，由于是做regression而不是classification，因此在这里输出层选取的激励函数就是f(x)=x。BP神经网络的具体原理此处不再介绍。

 

   import numpy as np

     

    class NeuralNetwork(object):

        def __init__(self, input_nodes, hidden_nodes, output_nodes, learning_rate):

            # Set number of nodes in input, hidden and output layers.设定输入层、隐藏层和输出层的node数目

            self.input_nodes = input_nodes

            self.hidden_nodes = hidden_nodes

            self.output_nodes = output_nodes

     

            # Initialize weights，初始化权重和学习速率

            self.weights_input_to_hidden = np.random.normal(0.0, self.hidden_nodes**-0.5, 

                                           ( self.hidden_nodes, self.input_nodes))

     

            self.weights_hidden_to_output = np.random.normal(0.0, self.output_nodes**-0.5, 

                                           (self.output_nodes, self.hidden_nodes))

            self.lr = learning_rate

            

            # 隐藏层的激励函数为sigmoid函数，Activation function is the sigmoid function

            self.activation_function = (lambda x: 1/(1 np.exp(-x)))

        

        def train(self, inputs_list, targets_list):