建立卷积神经网络；使用训练样本对卷积神经网络进行训练；使用测试样本对卷积神经网络进行测试；卷积神经网络的前向计算过程；计算目标函数值，以及目标函数对权值和偏置的偏导数；更新网络的权值和偏置。(A convolutional neural network; convolutional neural network is trained using the training samples; test the convolutional neural network using the test sample; convolutional neural network prior to the calculation process; calculating the objective function value, and the objective function of the weights and bias of the partial derivative; more new network weights and bias.)