The implement of Neural Network

simpleNN.py

#!/usr/bin/env python
#coding: utf-8

import numpy as np

np.random.seed(1)

def sigmoid(x):
    return 1/(1 + np.exp(-x))

def ForwardComputation(X, w0, w1):
    v0 = X 
    z1 = np.dot(X, w0)
    v1 = sigmoid(z1)
    z2 = np.dot(v1, w1) 
    v2 = sigmoid(z2)
    return v2

def simpleNN():
    X = np.array([[0,0,1], [0,1,1], [1,0,1],[1,1,1]])
    y = np.array([[0,0,1,1]]).T
    W0 = 2*np.random.random((3,4)) - 1
    W1 = 2*np.random.random((4,1)) - 1
    for i in xrange(10000):
        z1 = np.dot(X, W0)
        v1 = sigmoid(z1)
        z2 = np.dot(v1, W1)
        v2 = sigmoid(z2)
        l2_error = (y - v2)*(v2 * (1-v2))
        l1_error = l2_error.dot(W1.T) * (v1 * (1-v1))
        W1 += v1.T.dot(l2_error)
        W0 += X.T.dot(l1_error)
    return W0, W1

if __name__ == '__main__':
    W0, W1 = simpleNN() 
    print W0
    print W1
    X = np.array([[0,0,1], [0,1,1], [1,0,1],[1,1,1]])
    print ForwardComputation(X, W0, W1)