快捷導(dǎo)航

Python編程實(shí)現(xiàn)的簡(jiǎn)單神經(jīng)網(wǎng)絡(luò)算法示例

更新時(shí)間：2018年01月26日 11:04:31 作者：Nani_xiao

這篇文章主要介紹了Python編程實(shí)現(xiàn)的簡(jiǎn)單神經(jīng)網(wǎng)絡(luò)算法,結(jié)合實(shí)例形式分析了神經(jīng)網(wǎng)絡(luò)算法的原理及Python相關(guān)算法實(shí)現(xiàn)技巧,需要的朋友可以參考下

本文實(shí)例講述了Python編程實(shí)現(xiàn)的簡(jiǎn)單神經(jīng)網(wǎng)絡(luò)算法。分享給大家供大家參考，具體如下：

python實(shí)現(xiàn)二層神經(jīng)網(wǎng)絡(luò)

包括輸入層和輸出層

# -*- coding:utf-8 -*-
#! python2
import numpy as np
#sigmoid function
def nonlin(x, deriv = False):
 if(deriv == True):
  return x*(1-x)
 return 1/(1+np.exp(-x))
#input dataset
x = np.array([[0,0,1],
    [0,1,1],
    [1,0,1],
    [1,1,1]])
#output dataset
y = np.array([[0,0,1,1]]).T
np.random.seed(1)
#init weight value
syn0 = 2*np.random.random((3,1))-1
print "腳本之家測(cè)試結(jié)果："
for iter in xrange(100000):
 l0 = x       #the first layer,and the input layer
 l1 = nonlin(np.dot(l0,syn0)) #the second layer,and the output layer
 l1_error = y-l1
 l1_delta = l1_error*nonlin(l1,True)
 syn0 += np.dot(l0.T, l1_delta)
print "outout after Training:"
print l1

這里，

l0:輸入層
l1:輸出層
syn0:初始權(quán)值
l1_error:誤差
l1_delta:誤差校正系數(shù)
func nonlin:sigmoid函數(shù)

這里迭代次數(shù)為100時(shí)，預(yù)測(cè)結(jié)果為

迭代次數(shù)為1000時(shí)，預(yù)測(cè)結(jié)果為：

迭代次數(shù)為10000，預(yù)測(cè)結(jié)果為：

迭代次數(shù)為100000，預(yù)測(cè)結(jié)果為：

可見迭代次數(shù)越多，預(yù)測(cè)結(jié)果越接近理想值，當(dāng)時(shí)耗時(shí)也越長(zhǎng)。

python實(shí)現(xiàn)三層神經(jīng)網(wǎng)絡(luò)

包括輸入層、隱含層和輸出層

# -*- coding:utf-8 -*-
#! python2
import numpy as np
def nonlin(x, deriv = False):
 if(deriv == True):
  return x*(1-x)
 else:
  return 1/(1+np.exp(-x))
#input dataset
X = np.array([[0,0,1],
    [0,1,1],
    [1,0,1],
    [1,1,1]])
#output dataset
y = np.array([[0,1,1,0]]).T
syn0 = 2*np.random.random((3,4)) - 1 #the first-hidden layer weight value
syn1 = 2*np.random.random((4,1)) - 1 #the hidden-output layer weight value
print "腳本之家測(cè)試結(jié)果："
for j in range(60000):
 l0 = X      #the first layer,and the input layer
 l1 = nonlin(np.dot(l0,syn0)) #the second layer,and the hidden layer
 l2 = nonlin(np.dot(l1,syn1)) #the third layer,and the output layer
 l2_error = y-l2  #the hidden-output layer error
 if(j%10000) == 0:
  print "Error:"+str(np.mean(l2_error))
 l2_delta = l2_error*nonlin(l2,deriv = True)
 l1_error = l2_delta.dot(syn1.T)  #the first-hidden layer error
 l1_delta = l1_error*nonlin(l1,deriv = True)
 syn1 += l1.T.dot(l2_delta)
 syn0 += l0.T.dot(l1_delta)
print "outout after Training:"
print l2

運(yùn)行結(jié)果：