自己编写RBF神经网络程序，RBF神经网络隐层采用标准Gaussian径向基函数，输出层采用线性激活函数，其中数据中心、扩展常数和输出权值均用梯度法求解，它们的学习率均为0.001。其中隐节点数选为10，初始输出权值取[-0.1，0.1]内的随机值，初始数据中心取[-1，1]内的随机值，初始扩展常数取[0.1，0.3]内的随机值，输入采用[0 1]的随机阶跃输入(Write your own RBF neural network, RBF neural network hidden layer using standard Gaussian radial basis function, the output layer using a linear activation function, the data center, and the output weights are constant expansion with the gradient method, the learning rate is 0.001. The number of hidden nodes is 10, the initial output value [-0.1, random value of 0.1], initial data center [-1, random value of 1], the initial expansion constant of [0.1, a random value within 0.3], using a random order [0 1] step input)