程序运行时matlab命令窗口的内容.txt

”BP.m“文件是BP神经网络整个模型的源程序； “train.fig”是训练时最后得到的图片； “程序运行的人口数量原始数据.fig”是预测结果绘制的图； “程序运行时matlab命令窗口的内

TRAINGDX, Epoch 0/10000, MSE 0.485491/1e-006, Gradient 1.5531/1e-006
TRAINGDX, Epoch 25/10000, MSE 0.193909/1e-006, Gradient 0.512183/1e-006
TRAINGDX, Epoch 50/10000, MSE 0.0715114/1e-006, Gradient 0.175173/1e-006
TRAINGDX, Epoch 75/10000, MSE 0.0184612/1e-006, Gradient 0.0576844/1e-006
TRAINGDX, Epoch 100/10000, MSE 0.00260524/1e-006, Gradient 0.0127205/1e-006
TRAINGDX, Epoch 125/10000, MSE 0.000246867/1e-006, Gradient 0.0019373/1e-006
TRAINGDX, Epoch 150/10000, MSE 0.000123706/1e-006, Gradient 0.00507354/1e-006
TRAINGDX, Epoch 175/10000, MSE 0.000116049/1e-006, Gradient 0.00301195/1e-006
TRAINGDX, Epoch 200/10000, MSE 0.000101497/1e-006, Gradient 0.00103036/1e-006
TRAINGDX, Epoch 225/10000, MSE 6.88102e-005/1e-006, Gradient 0.000786054/1e-006
TRAINGDX, Epoch 250/10000, MSE 4.61095e-005/1e-006, Gradient 0.00205889/1e-006
TRAINGDX, Epoch 275/10000, MSE 4.42204e-005/1e-006, Gradient 0.000761046/1e-006
TRAINGDX, Epoch 300/10000, MSE 4.0428e-005/1e-006, Gradient 0.000592715/1e-006
TRAINGDX, Epoch 325/10000, MSE 3.00625e-005/1e-006, Gradient 0.000467441/1e-006
TRAINGDX, Epoch 350/10000, MSE 2.0882e-005/1e-006, Gradient 0.00171418/1e-006
TRAINGDX, Epoch 375/10000, MSE 2.00944e-005/1e-006, Gradient 0.000545846/1e-006
TRAINGDX, Epoch 400/10000, MSE 1.87138e-005/1e-006, Gradient 0.000394783/1e-006
TRAINGDX, Epoch 425/10000, MSE 1.48127e-005/1e-006, Gradient 0.000317218/1e-006
TRAINGDX, Epoch 450/10000, MSE 9.65641e-006/1e-006, Gradient 0.00226225/1e-006
TRAINGDX, Epoch 475/10000, MSE 9.13826e-006/1e-006, Gradient 0.000436552/1e-006
TRAINGDX, Epoch 500/10000, MSE 8.71121e-006/1e-006, Gradient 0.000248653/1e-006
TRAINGDX, Epoch 525/10000, MSE 7.4569e-006/1e-006, Gradient 0.000208825/1e-006
TRAINGDX, Epoch 550/10000, MSE 4.96604e-006/1e-006, Gradient 0.00165383/1e-006
TRAINGDX, Epoch 575/10000, MSE 4.87989e-006/1e-006, Gradient 0.00158295/1e-006
TRAINGDX, Epoch 600/10000, MSE 4.55352e-006/1e-006, Gradient 0.000355931/1e-006
TRAINGDX, Epoch 625/10000, MSE 4.13114e-006/1e-006, Gradient 0.000142734/1e-006
TRAINGDX, Epoch 650/10000, MSE 3.0491e-006/1e-006, Gradient 0.000207076/1e-006
TRAINGDX, Epoch 675/10000, MSE 2.89908e-006/1e-006, Gradient 0.000108889/1e-006
TRAINGDX, Epoch 700/10000, MSE 2.83463e-006/1e-006, Gradient 0.000177645/1e-006
TRAINGDX, Epoch 725/10000, MSE 2.66008e-006/1e-006, Gradient 0.000107797/1e-006
TRAINGDX, Epoch 750/10000, MSE 2.18814e-006/1e-006, Gradient 8.40793e-005/1e-006
TRAINGDX, Epoch 775/10000, MSE 2.05976e-006/1e-006, Gradient 0.000897926/1e-006
TRAINGDX, Epoch 800/10000, MSE 1.97744e-006/1e-006, Gradient 0.000113253/1e-006
TRAINGDX, Epoch 825/10000, MSE 1.9143e-006/1e-006, Gradient 8.11492e-005/1e-006
TRAINGDX, Epoch 850/10000, MSE 1.73559e-006/1e-006, Gradient 6.1758e-005/1e-006
TRAINGDX, Epoch 875/10000, MSE 1.59312e-006/1e-006, Gradient 0.000474688/1e-006
TRAINGDX, Epoch 900/10000, MSE 1.56862e-006/1e-006, Gradient 0.000191387/1e-006
TRAINGDX, Epoch 925/10000, MSE 1.54503e-006/1e-006, Gradient 9.39367e-005/1e-006
TRAINGDX, Epoch 950/10000, MSE 1.48558e-006/1e-006, Gradient 4.65935e-005/1e-006
TRAINGDX, Epoch 975/10000, MSE 1.41909e-006/1e-006, Gradient 0.000888072/1e-006
TRAINGDX, Epoch 1000/10000, MSE 1.37491e-006/1e-006, Gradient 0.000455434/1e-006
TRAINGDX, Epoch 1025/10000, MSE 1.35361e-006/1e-006, Gradient 0.000110202/1e-006
TRAINGDX, Epoch 1050/10000, MSE 1.3341e-006/1e-006, Gradient 3.49585e-005/1e-006
TRAINGDX, Epoch 1075/10000, MSE 1.28313e-006/1e-006, Gradient 2.8553e-005/1e-006
TRAINGDX, Epoch 1100/10000, MSE 1.29515e-006/1e-006, Gradient 0.000712259/1e-006
TRAINGDX, Epoch 1125/10000, MSE 1.25782e-006/1e-006, Gradient 0.000117182/1e-006
TRAINGDX, Epoch 1150/10000, MSE 1.25111e-006/1e-006, Gradient 2.36672e-005/1e-006
TRAINGDX, Epoch 1175/10000, MSE 1.23518e-006/1e-006, Gradient 2.07856e-005/1e-006
TRAINGDX, Epoch 1200/10000, MSE 1.25336e-006/1e-006, Gradient 0.000774752/1e-006
TRAINGDX, Epoch 1225/10000, MSE 1.21216e-006/1e-006, Gradient 0.000153392/1e-006
TRAINGDX, Epoch 1250/10000, MSE 1.20886e-006/1e-006, Gradient 4.15751e-005/1e-006
TRAINGDX, Epoch 1275/10000, MSE 1.20491e-006/1e-006, Gradient 1.93713e-005/1e-006
TRAINGDX, Epoch 1300/10000, MSE 1.19471e-006/1e-006, Gradient 1.44784e-005/1e-006
TRAINGDX, Epoch 1325/10000, MSE 1.22148e-006/1e-006, Gradient 0.000679126/1e-006
TRAINGDX, Epoch 1350/10000, MSE 1.19115e-006/1e-006, Gradient 0.000185197/1e-006
TRAINGDX, Epoch 1375/10000, MSE 1.18779e-006/1e-006, Gradient 1.10934e-005/1e-006
TRAINGDX, Epoch 1400/10000, MSE 1.18555e-006/1e-006, Gradient 1.07978e-005/1e-006
TRAINGDX, Epoch 1425/10000, MSE 1.18149e-006/1e-006, Gradient 0.000153224/1e-006
TRAINGDX, Epoch 1450/10000, MSE 1.17942e-006/1e-006, Gradient 1.55072e-005/1e-006
TRAINGDX, Epoch 1475/10000, MSE 1.18033e-006/1e-006, Gradient 0.000132314/1e-006
TRAINGDX, Epoch 1500/10000, MSE 1.17855e-006/1e-006, Gradient 1.70397e-005/1e-006
TRAINGDX, Epoch 1525/10000, MSE 1.17723e-006/1e-006, Gradient 6.39341e-006/1e-006
TRAINGDX, Epoch 1550/10000, MSE 1.19959e-006/1e-006, Gradient 0.000595472/1e-006
TRAINGDX, Epoch 1575/10000, MSE 1.18461e-006/1e-006, Gradient 0.000375348/1e-006
TRAINGDX, Epoch 1600/10000, MSE 1.17491e-006/1e-006, Gradient 6.19754e-005/1e-006
TRAINGDX, Epoch 1625/10000, MSE 1.17441e-006/1e-006, Gradient 2.04427e-005/1e-006
TRAINGDX, Epoch 1650/10000, MSE 1.17385e-006/1e-006, Gradient 5.38945e-006/1e-006
TRAINGDX, Epoch 1675/10000, MSE 1.20414e-006/1e-006, Gradient 0.000671662/1e-006
TRAINGDX, Epoch 1700/10000, MSE 1.1859e-006/1e-006, Gradient 0.000435912/1e-006
TRAINGDX, Epoch 1725/10000, MSE 1.17266e-006/1e-006, Gradient 3.42248e-005/1e-006
TRAINGDX, Epoch 1750/10000, MSE 1.17252e-006/1e-006, Gradient 2.5184e-005/1e-006
TRAINGDX, Epoch 1775/10000, MSE 1.17227e-006/1e-006, Gradient 6.08345e-006/1e-006
TRAINGDX, Epoch 1800/10000, MSE 1.17517e-006/1e-006, Gradient 0.000219379/1e-006
TRAINGDX, Epoch 1825/10000, MSE 1.1719e-006/1e-006, Gradient 4.25843e-005/1e-006
TRAINGDX, Epoch 1850/10000, MSE 1.17244e-006/1e-006, Gradient 9.89117e-005/1e-006
TRAINGDX, Epoch 1875/10000, MSE 1.17173e-006/1e-006, Gradient 1.32846e-005/1e-006
TRAINGDX, Epoch 1900/10000, MSE 1.17165e-006/1e-006, Gradient 5.67937e-006/1e-006
TRAINGDX, Epoch 1925/10000, MSE 1.17148e-006/1e-006, Gradient 2.18767e-006/1e-006
TRAINGDX, Epoch 1950/10000, MSE 1.19599e-006/1e-006, Gradient 0.000593754/1e-006
TRAINGDX, Epoch 1975/10000, MSE 1.17409e-006/1e-006, Gradient 0.000197148/1e-006
TRAINGDX, Epoch 2000/10000, MSE 1.17149e-006/1e-006, Gradient 4.19869e-005/1e-006
TRAINGDX, Epoch 2025/10000, MSE 1.17135e-006/1e-006, Gradient 9.37354e-006/1e-006
TRAINGDX, Epoch 2050/10000, MSE 1.1713e-006/1e-006, Gradient 1.1776e-006/1e-006
TRAINGDX, Epoch 2067/10000, MSE 1.17125e-006/1e-006, Gradient 9.63656e-007/1e-006
TRAINGDX, Minimum gradient reached, performance goal was not met.

网络拟合的结果
A2 =
  Columns 1 through 6 
   0.12071217582085   0.12295214469788   0.12441196739804   0.12486636778906   0.12474660596745   0.12448107801549
  Columns 7 through 10 
   0.12427368525228   0.12617380743475   0.12571450226430   0.12529187327705
数据训练后的网络拟合结果误差
E =
  Columns 1 through 6 
   0.00040882417915  -0.00056314469788  -0.00078596739804  -0.00005636778906   0.00103939403255   0.00210192198451
  Columns 7 through 10 
  -0.00221778525228  -0.00027870743475   0.00033529773570   0.00001462672295
均方差误差性能值
MSE =
    1.171249499453727e-006
验证数据
2004年的数据为：
A2004 =
   0.12529187327705
E的值为:
E2004 =
    1.462672295121648e-005
>> Y
Y =
  1.0e+006 *
  Columns 1 through 6 
   1.15823000000000   1.17171000000000   1.18517000000000   1.19850000000000   1.21121000000000   1.22389000000000
  Columns 7 through 12 
   1.23626000000000   1.24810000000000   1.25786000000000   1.26583000000000   1.22055900000000   1.25895100000000
  Columns 13 through 18 
   1.26049800000000   1.25291873277049   1.24631518736534   1.26006993816868   1.25875247600815   1.25595458696701
  Columns 19 through 24 
   1.25328497581953   1.25894787904566   1.25727907328395   1.25697234185994   1.25539654740576   1.25817739550881
  Columns 25 through 30 
   1.25671471428789   1.25729538050113   1.25614781478575   1.25775293491657   1.25659473881520   1.25736448944740
  Columns 31 through 36 
   1.25646300909140   1.25751838087517   1.25662672018949   1.25734207636972   1.25662305624323   1.25737910724140
  Columns 37 through 42 
   1.25669448336217   1.25729262179336   1.25672081229930   1.25728858335841   1.25676055515911   1.25724086103649
  Columns 43 through 48 
   1.25678877881638   1.25722501098349   1.25681572834765   1.25719512552605   1.25683937733309   1.25717797622788
  Columns 49 through 54 
   1.25685958029434   1.25715727687974   1.25687818286419   1.25714212541317   1.25689387709885   1.25712685693266
  Columns 55 through 60 
   1.25690828562135   1.25711438256460   1.25692058388922   1.25710274065971   1.25693173133869   1.25709276294269
  Columns 61 through 66 
   1.25694137187904   1.25708374742858   1.25695001693282   1.25707586542128   1.25695756398306   1.25706883732491
  Columns 67 through 72 
   1.25696428525197   1.25706264471850   1.25697018660105   1.25705715185721   1.25697542186580   1.25705229833486
  Columns 73 through 78 
   1.25698003328210   1.25704800177512   1.25698411600686   1.25704420201163   1.25698771838758   1.25704084070217
  Columns 79 through 84 
   1.25699090469770   1.25703786754760   1.25699371862672   1.25703523813262   1.25699620650146   1.25703291246864
  Columns 85 through 90 
   1.25699840462462   1.25703085588202   1.25700034773510   1.25702903704382   1.25700206495018   1.25702742871876
>>