本文实例讲述了Python实现的人工神经网络算法。分享给大家供大家参考,具体如下:
注意:本程序使用Python3编写,额外需要安装numpy工具包用于矩阵运算,未测试python2是否可以运行。
本程序实现了《机器学习》书中所述的反向传播算法训练人工神经网络,理论部分请参考我的读书笔记。
在本程序中,目标函数是由一个输入x和两个输出y组成,
x是在范围【-3.14, 3.14】之间随机生成的实数,而两个y值分别对应 y1 = sin(x),y2 = 1。
随机生成一万份训练样例,经过网络的学习训练后,再用随机生成的五份测试数据验证训练结果。
调节算法的学习速率,以及隐藏层个数、隐藏层大小,训练新的网络,可以观察到参数对于学习结果的影响。
算法代码如下:
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
|
#!usr/bin/env python3
# -*- coding:utf-8 -*-
import numpy as np
import math
# definition of sigmoid funtion
# numpy.exp work for arrays.
def sigmoid(x):
return 1 / ( 1 + np.exp( - x))
# definition of sigmoid derivative funtion
# input must be sigmoid function's result
def sigmoid_output_to_derivative(result):
return result * ( 1 - result)
# init training set
def getTrainingSet(nameOfSet):
setDict = {
"sin" : getSinSet(),
}
return setDict[nameOfSet]
def getSinSet():
x = 6.2 * np.random.rand( 1 ) - 3.14
x = x.reshape( 1 , 1 )
# y = np.array([5 *x]).reshape(1,1)
# y = np.array([math.sin(x)]).reshape(1,1)
y = np.array([math.sin(x), 1 ]).reshape( 1 , 2 )
return x, y
def getW(synapse, delta):
resultList = []
# 遍历隐藏层每个隐藏单元对每个输出的权值,比如8个隐藏单元,每个隐藏单元对两个输出各有2个权值
for i in range (synapse.shape[ 0 ]):
resultList.append(
(synapse[i,:] * delta). sum ()
)
resultArr = np.array(resultList).reshape( 1 , synapse.shape[ 0 ])
return resultArr
def getT(delta, layer):
result = np.dot(layer.T, delta)
return result
def backPropagation(trainingExamples, etah, input_dim, output_dim, hidden_dim, hidden_num):
# 可行条件
if hidden_num < 1 :
print ( "隐藏层数不得小于1" )
return
# 初始化网络权重矩阵,这个是核心
synapseList = []
# 输入层与隐含层1
synapseList.append( 2 * np.random.random((input_dim,hidden_dim)) - 1 )
# 隐含层1与隐含层2, 2->3,,,,,,n-1->n
for i in range (hidden_num - 1 ):
synapseList.append( 2 * np.random.random((hidden_dim,hidden_dim)) - 1 )
# 隐含层n与输出层
synapseList.append( 2 * np.random.random((hidden_dim,output_dim)) - 1 )
iCount = 0
lastErrorMax = 99999
# while True:
for i in range ( 10000 ):
errorMax = 0
for x, y in trainingExamples:
iCount + = 1
layerList = []
# 正向传播
layerList.append(
sigmoid(np.dot(x,synapseList[ 0 ]))
)
for j in range (hidden_num):
layerList.append(
sigmoid(np.dot(layerList[ - 1 ],synapseList[j + 1 ]))
)
# 对于网络中的每个输出单元k,计算它的误差项
deltaList = []
layerOutputError = y - layerList[ - 1 ]
# 收敛条件
errorMax = layerOutputError. sum () if layerOutputError. sum () > errorMax else errorMax
deltaK = sigmoid_output_to_derivative(layerList[ - 1 ]) * layerOutputError
deltaList.append(deltaK)
iLength = len (synapseList)
for j in range (hidden_num):
w = getW(synapseList[iLength - 1 - j], deltaList[j])
delta = sigmoid_output_to_derivative(layerList[iLength - 2 - j]) * w
deltaList.append(delta)
# 更新每个网络权值w(ji)
for j in range ( len (synapseList) - 1 , 0 , - 1 ):
t = getT(deltaList[iLength - 1 - j], layerList[j - 1 ])
synapseList[j] = synapseList[j] + etah * t
t = getT(deltaList[ - 1 ], x)
synapseList[ 0 ] = synapseList[ 0 ] + etah * t
print ( "最大输出误差:" )
print (errorMax)
if abs (lastErrorMax - errorMax) < 0.0001 :
print ( "收敛了" )
print ( "####################" )
break
lastErrorMax = errorMax
# 测试训练好的网络
for i in range ( 5 ):
xTest, yReal = getSinSet()
layerTmp = sigmoid(np.dot(xTest,synapseList[ 0 ]))
for j in range ( 1 , len (synapseList), 1 ):
layerTmp = sigmoid(np.dot(layerTmp,synapseList[j]))
yTest = layerTmp
print ( "x:" )
print (xTest)
print ( "实际的y:" )
print (yReal)
print ( "神经元网络输出的y:" )
print (yTest)
print ( "最终输出误差:" )
print (np. abs (yReal - yTest))
print ( "#####################" )
print ( "迭代次数:" )
print (iCount)
if __name__ = = '__main__' :
import datetime
tStart = datetime.datetime.now()
# 使用什么样的训练样例
nameOfSet = "sin"
x, y = getTrainingSet(nameOfSet)
# setting of parameters
# 这里设置了学习速率。
etah = 0.01
# 隐藏层数
hidden_num = 2
# 网络输入层的大小
input_dim = x.shape[ 1 ]
# 隐含层的大小
hidden_dim = 100
# 输出层的大小
output_dim = y.shape[ 1 ]
# 构建训练样例
trainingExamples = []
for i in range ( 10000 ):
x, y = getTrainingSet(nameOfSet)
trainingExamples.append((x, y))
# 开始用反向传播算法训练网络
backPropagation(trainingExamples, etah, input_dim, output_dim, hidden_dim, hidden_num)
tEnd = datetime.datetime.now()
print ( "time cost:" )
print (tEnd - tStart)
|
希望本文所述对大家Python程序设计有所帮助。
原文链接:http://blog.csdn.net/miangangzhen/article/details/51281989