点击查看完整代码http://www.daimapi.com/neuralnetwork2_1/

      径向基神经网络（Radial Basis Function Network）,简写为RBF，该代码不使用任何第三方深度学习工具包实现，利用Python3实现。

# -*- coding: utf-8 -*-
from scipy import *
from scipy.linalg import norm, pinv
from matplotlib import pyplot as plt

class RBF:
    def __init__(self, indim, numCenters, outdim):
        self.indim = indim
        self.outdim = outdim
        self.numCenters = numCenters
        self.centers = [random.uniform(-1, 1, indim) for i in range(numCenters)]
        self.beta = 8
        self.W = random.random((self.numCenters, self.outdim))

    def _basisfunc(self, c, d):
        assert len(d) == self.indim
        return exp(-self.beta * norm(c-d)**2)

    def _calcAct(self, X):
        # 计算RBFs的激活函数值
        G = zeros((X.shape[0], self.numCenters), float)
        for ci, c in enumerate(self.centers):
            for xi, x in enumerate(X):
                G[xi,ci] = self._basisfunc(c, x)
        return G

    def train(self, X, Y):
        """ X: n x indim维的矩阵
            y: n x 1维的列向量"""

        # 从训练集随机选择中心向量
        rnd_idx = random.permutation(X.shape[0])[:self.numCenters]
        self.centers = [X[i,:] for i in rnd_idx]

        print("center", self.centers)
        # 计算RBFs的激活函数值
        G = self._calcAct(X)
        print(G)

        # 计算输出层的权值
        self.W = dot(pinv(G), Y)

    def test(self, X):
        """ X: n x indim维的矩阵 """

        G = self._calcAct(X)
        Y = dot(G, self.W)
        return Y