Introduction - If you have any usage issues, please Google them yourself
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