( A, B )---5*30*2---( 1, 0 )( 0, 1 )
做一个网络，输入为5个点，训练集A,B各有两张图片。让B的两张图片全是0.排列组合A，记录迭代次数平均值的变化。
迭代了1024组，共收集到33组不同的数据，其中对称的部分有17组，不对称的有15组.31*31-0*0是分界线。
| 4*30*2 | 5*30*2 | |
| 256 | 1024 | |
| 21 | 33 | |
| 不对称 | 8 | 15 |
| 对称 | 12 | 17 |
这次继续用计算质心的办法去拟合迭代次数，
| 0 | 1 | 2 | 3 | 4 | |||||||||
| 0 | 1 | 0 | 1 | 0 | 10*22-0*0 | ||||||||
| 1 | 0 | 1 | 1 | 0 | 10*22-0*0 | ||||||||
| 坐标 | 质量 | 坐标*质量 | |||||||||||
| 0 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | ||||
| 1 | 1.5 | 0 | 1.5 | 1 | 1 | 1 | 1.5 | 0 | 1.5 | ||||
| 2 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | ||||
| 3 | 3.5 | 0 | 1.5 | 1 | 1 | 1 | 3.5 | 0 | 1.5 | ||||
| 4 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | ||||
| 0 | 0.5 | 0 | 0.5 | 1 | 1 | 1 | 0.5 | 0 | 0.5 | ||||
| 1 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | ||||
| 2 | 2.5 | 0 | 0.5 | 1 | 1 | 1 | 2.5 | 0 | 0.5 | ||||
| 3 | 3.5 | 0 | 0.5 | 1 | 1 | 1 | 3.5 | 0 | 0.5 | ||||
| 4 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | ||||
| 12 | 0 | 4.5 | |||||||||||
| 质心坐标 | |||||||||||||
| 5 | 2.3 | 0 | 0.9 | ||||||||||
两行x的坐标都是0.5，1.5，2.5，3.5，4.5，y坐标为0，z坐标第一行是0.5，第二行是1.5.则10*22-0*0的质心为(2.3,0,0.9).
得到数据为
| 差值结构 | 网络 | 迭代次数 | 质心x | y | z | |||||||||
| 0 | 0 | 0 | 1 | 0 | 2*31-0*0 | 4766.377 | 6 | 1 | 5 | 2.16667 | 0 | 0.66667 | ||
| 1 | 1 | 1 | 1 | 1 | 2*31-0*0 | 4766.377 | 6 | 1 | 5 | |||||
| 6 | 1 | 5 | ||||||||||||
| 0 | 1 | 0 | 0 | 0 | 8*30-0*0 | 5682.156 | 5 | 1 | 4 | 1.7 | 0 | 0.7 | ||
| 1 | 1 | 1 | 1 | 0 | 8*30-0*0 | 5682.156 | 5 | 1 | 4 | |||||
| 5 | 1 | 4 | ||||||||||||
| 0 | 0 | 0 | 1 | 0 | 2*14-0*0 | 7016.286 | 4 | 1 | 3 | 1.25 | 0 | 0.75 | ||
| 0 | 1 | 1 | 1 | 0 | 2*14-0*0 | 7016.286 | 4 | 1 | 3 | |||||
| 4 | 1 | 3 | ||||||||||||
| 0 | 1 | 0 | 1 | 0 | 10*31-0*0 | 8185.151 | 7 | 2 | 5 | 2.5 | 0 | 0.78571 | ||
| 1 | 1 | 1 | 1 | 1 | 10*31-0*0 | 8185.151 | 7 | 2 | 5 | |||||
| 7 | 2 | 5 | ||||||||||||
| 0 | 1 | 0 | 1 | 0 | 10*30-0*0 | 9968.608 | 6 | 2 | 4 | 2.16667 | 0 | 0.83333 | ||
| 1 | 1 | 1 | 1 | 0 | 10*30-0*0 | 9968.608 | 6 | 2 | 4 | |||||
| 6 | 2 | 4 | ||||||||||||
| 0 | 0 | 1 | 0 | 0 | 4*12-0*0 | 10341.13 | 3 | 1 | 2 | 2.16667 | 0 | 0.83333 | ||
| 0 | 1 | 1 | 0 | 0 | 4*12-0*0 | 10341.13 | 3 | 1 | 2 | |||||
| 3 | 1 | 2 | ||||||||||||
| 1 | 0 | 1 | 0 | 1 | 21*31-0*0 | 11793.89 | 8 | 3 | 5 | 2.5 | 0 | 0.875 | ||
| 1 | 1 | 1 | 1 | 1 | 21*31-0*0 | 11793.89 | 8 | 3 | 5 | |||||
| 8 | 3 | 5 | ||||||||||||
| 0 | 0 | 1 | 0 | 1 | 5*7-0*0 | 13311.64 | 5 | 2 | 3 | 3.5 | 0 | 0.9 | ||
| 0 | 0 | 1 | 1 | 1 | 5*7-0*0 | 13311.64 | 5 | 2 | 3 | |||||
| 5 | 2 | 3 | ||||||||||||
| 0 | 1 | 0 | 0 | 1 | 9*23-0*0 | 14500.69 | 6 | 2 | 4 | 2.83333 | 0 | 0.83333 | ||
| 1 | 0 | 1 | 1 | 1 | 9*23-0*0 | 14500.69 | 6 | 2 | 4 | |||||
| 6 | 2 | 4 | ||||||||||||
| 0 | 1 | 0 | 0 | 0 | 8*23-0*0 | 14608.61 | 5 | 1 | 4 | 2.5 | 0 | 0.7 | ||
| 1 | 0 | 1 | 1 | 1 | 8*23-0*0 | 14608.61 | 5 | 1 | 4 | |||||
| 5 | 1 | 4 | ||||||||||||
| 1 | 0 | 0 | 1 | 1 | 19*27-0*0 | 14486.38 | 7 | 3 | 4 | 2.64286 | 0 | 0.92857 | ||
| 1 | 1 | 0 | 1 | 1 | 19*27-0*0 | 14486.38 | 7 | 3 | 4 | |||||
| 7 | 3 | 4 | ||||||||||||
| 1 | 1 | 0 | 1 | 1 | 27*31-0*0 | 15154.8 | 9 | 4 | 5 | 2.5 | 0 | 0.94444 | ||
| 1 | 1 | 1 | 1 | 1 | 27*31-0*0 | 15154.8 | 9 | 4 | 5 | |||||
| 9 | 4 | 5 | ||||||||||||
| 0 | 1 | 0 | 1 | 1 | 11*23-0*0 | 16791.92 | 7 | 3 | 4 | 2.92857 | 0 | 0.92857 | ||
| 1 | 0 | 1 | 1 | 1 | 11*23-0*0 | 16791.92 | 7 | 3 | 4 | |||||
| 7 | 3 | 4 | ||||||||||||
| 0 | 1 | 0 | 0 | 0 | 8*22-0*0 | 17517.73 | 4 | 1 | 3 | 3 | 0 | 0.75 | ||
| 1 | 0 | 1 | 1 | 0 | 8*22-0*0 | 17517.73 | 4 | 1 | 3 | |||||
| 4 | 1 | 3 | ||||||||||||
| 0 | 1 | 0 | 1 | 0 | 10*22-0*0 | 17793.41 | 5 | 2 | 3 | 2.1 | 0 | 0.9 | ||
| 1 | 0 | 1 | 1 | 0 | 10*22-0*0 | 17793.41 | 5 | 2 | 3 | |||||
| 5 | 2 | 3 | ||||||||||||
| 1 | 1 | 1 | 1 | 1 | 31*31-0*0 | 18794.76 | # | 5 | 5 | |||||
| 1 | 1 | 1 | 1 | 1 | 31*31-0*0 | 18794.76 | # | 5 | 5 | 1024 | ||||
| # | 5 | 5 | ||||||||||||
| 1 | 0 | 1 | 1 | 1 | 23*23-0*0 | 19454.11 | 8 | 4 | 4 | |||||
| 1 | 0 | 1 | 1 | 1 | 23*23-0*0 | 19454.11 | 8 | 4 | 4 | |||||
| 8 | 4 | 4 | ||||||||||||
| 0 | 1 | 1 | 1 | 1 | 15*30-0*0 | 19855.73 | 8 | 4 | 4 | |||||
| 1 | 1 | 1 | 1 | 0 | 15*30-0*0 | 19855.73 | 8 | 4 | 4 | |||||
| 8 | 4 | 4 | ||||||||||||
| 1 | 1 | 1 | 0 | 0 | 28*28-0*0 | 20593.18 | 6 | 3 | 3 | |||||
| 1 | 1 | 1 | 0 | 0 | 28*28-0*0 | 20593.18 | 6 | 3 | 3 | |||||
| 6 | 3 | 3 | ||||||||||||
| 0 | 1 | 0 | 1 | 1 | 11*26-0*0 | 21390.39 | 6 | 3 | 3 | |||||
| 1 | 1 | 0 | 1 | 0 | 11*26-0*0 | 21390.39 | 6 | 3 | 3 | |||||
| 6 | 3 | 3 | ||||||||||||
| 1 | 0 | 1 | 0 | 1 | 21*10-0*0 | 21925.96 | 5 | 3 | 2 | |||||
| 0 | 1 | 0 | 1 | 0 | 21*10-0*0 | 21925.96 | 5 | 3 | 2 | |||||
| 5 | 3 | 2 | ||||||||||||
| 0 | 1 | 0 | 0 | 0 | 8*20-0*0 | 22413.93 | 3 | 1 | 2 | |||||
| 1 | 0 | 1 | 0 | 0 | 8*20-0*0 | 22413.93 | 3 | 1 | 2 | |||||
| 3 | 1 | 2 | ||||||||||||
| 0 | 0 | 1 | 1 | 1 | 7*28-0*0 | 22662.79 | 6 | 3 | 3 | |||||
| 1 | 1 | 1 | 0 | 0 | 7*28-0*0 | 22662.79 | 6 | 3 | 3 | |||||
| 6 | 3 | 3 | ||||||||||||
| 0 | 1 | 1 | 0 | 0 | 12*12-0*0 | 22636.98 | 4 | 2 | 2 | |||||
| 0 | 1 | 1 | 0 | 0 | 12*12-0*0 | 22636.98 | 4 | 2 | 2 | |||||
| 4 | 2 | 2 | ||||||||||||
| 0 | 0 | 1 | 0 | 1 | 5*20-0*0 | 24238.5 | 4 | 2 | 2 | |||||
| 1 | 0 | 1 | 0 | 0 | 5*20-0*0 | 24238.5 | 4 | 2 | 2 | |||||
| 4 | 2 | 2 | ||||||||||||
| 0 | 0 | 0 | 0 | 0 | 0*31-0*0 | 25756.47 | 5 | 0 | 5 | |||||
| 1 | 1 | 1 | 1 | 1 | 0*31-0*0 | 25756.47 | 5 | 0 | 5 | |||||
| 5 | 0 | 5 | ||||||||||||
| 0 | 0 | 0 | 0 | 0 | 0*30-0*0 | 27150.64 | 4 | 0 | 4 | |||||
| 1 | 1 | 1 | 1 | 0 | 0*30-0*0 | 27150.64 | 4 | 0 | 4 | |||||
| 4 | 0 | 4 | ||||||||||||
| 1 | 0 | 0 | 0 | 0 | 16*16-0*0 | 27122.25 | 2 | 1 | 1 | |||||
| 1 | 0 | 0 | 0 | 0 | 16*16-0*0 | 27122.25 | 2 | 1 | 1 | |||||
| 2 | 1 | 1 | ||||||||||||
| 0 | 1 | 0 | 1 | 0 | 10*5-0*0 | 27287.88 | 4 | 2 | 2 | |||||
| 0 | 0 | 1 | 0 | 1 | 10*5-0*0 | 27287.88 | 4 | 2 | 2 | |||||
| 4 | 2 | 2 | ||||||||||||
| 0 | 0 | 0 | 0 | 0 | 0*28-0*0 | 29376.11 | 3 | 0 | 3 | |||||
| 1 | 1 | 1 | 0 | 0 | 0*28-0*0 | 29376.11 | 3 | 0 | 3 | |||||
| 3 | 0 | 3 | ||||||||||||
| 0 | 0 | 0 | 0 | 0 | 0*24-0*0 | 32971.82 | 2 | 0 | 2 | |||||
| 1 | 1 | 0 | 0 | 0 | 0*24-0*0 | 32971.82 | 2 | 0 | 2 | |||||
| 2 | 0 | 2 | ||||||||||||
| 0 | 0 | 0 | 0 | 1 | 1*2-0*0 | 33618.72 | 2 | 1 | 1 | |||||
| 0 | 0 | 0 | 1 | 0 | 1*2-0*0 | 33618.72 | 2 | 1 | 1 | |||||
| 2 | 1 | 1 | ||||||||||||
| 0 | 0 | 0 | 0 | 0 | 0*4-0*0 | 40885.45 | 1 | 0 | 1 | |||||
| 0 | 0 | 1 | 0 | 0 | 0*4-0*0 | 40885.45 | 1 | 0 | 1 | |||||
| 1 | 0 | 1 |
不对称部分的15组可以拟合其中的10组。
| 网络 | 迭代次数 | 质心z |
| 2*31-0*0 | 4766.377 | 0.666667 |
| 8*30-0*0 | 5682.156 | 0.7 |
| 2*14-0*0 | 7016.286 | 0.75 |
| 10*31-0*0 | 8185.151 | 0.785714 |
| 10*30-0*0 | 9968.608 | 0.833333 |
| 4*12-0*0 | 10341.13 | 0.833333 |
| 21*31-0*0 | 11793.89 | 0.875 |
| 5*7-0*0 | 13311.64 | 0.9 |
| 19*27-0*0 | 14486.38 | 0.928571 |
| 27*31-0*0 | 15154.8 | 0.944444 |
拟合这两组数据
质心=0.0533463084569849*迭代次数**0.2981490239995757
0.9986715201061859 ****** 决定系数 r**2
但有5组数据异常
| 计算质心 | 约化z坐标 | 与1.5的差值 | ||||||||||||
| 0 | 1 | 0 | 0 | 1 | 9*23-0*0 | 14500.69 | 2.83 | 0 | 0.83 | 0.928578 | 2.07 | 0.57 | ||
| 1 | 0 | 1 | 1 | 1 | 9*23-0*0 | 14500.69 | ||||||||
| 0 | 1 | 0 | 0 | 0 | 8*23-0*0 | 14608.61 | 2.5 | 0 | 0.7 | 0.930633 | 2.65 | 1.15 | ||
| 1 | 0 | 1 | 1 | 1 | 8*23-0*0 | 14608.61 | ||||||||
| 0 | 1 | 0 | 1 | 1 | 11*23-0*0 | 16791.92 | 2.93 | 0 | 0.93 | 0.970094 | 1.8 | 0.3 | ||
| 1 | 0 | 1 | 1 | 1 | 11*23-0*0 | 16791.92 | ||||||||
| 0 | 1 | 0 | 0 | 0 | 8*22-0*0 | 17517.73 | 3 | 0 | 0.75 | 0.982411 | 2.42 | 0.92 | ||
| 1 | 0 | 1 | 1 | 0 | 8*22-0*0 | 17517.73 | ||||||||
| 0 | 1 | 0 | 1 | 0 | 10*22-0*0 | 17793.41 | 2.1 | 0 | 0.9 | 0.986995 | 1.93 | 0.43 | ||
| 1 | 0 | 1 | 1 | 0 | 10*22-0*0 | 17793.41 |
这5组里都有
| 0 | 1 | 0 |
| 1 | 0 | 1 |
2*5这样的对称结构。现在用这5组的迭代次数计算出这5组的质心，然后计算
| 0 | 1 | 0 |
| 1 | 0 | 1 |
对称结构第二行1的修正z坐标，用这个约化坐标重新计算10*22-0*0的质心为
| 0 | 1 | 2 | 3 | 4 | |||||||||
| 0 | 1 | 0 | 1 | 0 | 10*22-0*0 | ||||||||
| 1 | 0 | 1 | 1 | 0 | 10*22-0*0 | ||||||||
| 坐标 | 质量 | 坐标*质量 | |||||||||||
| 0 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | ||||
| 1 | 1.5 | 0 | 1.93 | 1 | 1 | 1 | 1.5 | 0 | 1.93 | ||||
| 2 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | ||||
| 3 | 3.5 | 0 | 1.5 | 1 | 1 | 1 | 3.5 | 0 | 1.5 | ||||
| 4 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | ||||
| 0 | 0.5 | 0 | 0.5 | 1 | 1 | 1 | 0.5 | 0 | 0.5 | ||||
| 1 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | ||||
| 2 | 2.5 | 0 | 0.5 | 1 | 1 | 1 | 2.5 | 0 | 0.5 | ||||
| 3 | 3.5 | 0 | 0.5 | 1 | 1 | 1 | 3.5 | 0 | 0.5 | ||||
| 4 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | ||||
| 12 | 0 | 4.93 | |||||||||||
| 质心坐标 | |||||||||||||
| 5 | 2.3 | 0 | 0.986 | ||||||||||
如果第二行只有1个1这个修正约为1，如果有两个1修正约为0.5，如果有3个1修正为0.3.
![[Android]Toolbar](https://img-blog.csdnimg.cn/0109e04b3afc44288ac659346e68a0a7.png)