BP神经网络算法的改进及在MATLAB中的实现

hanjuan007

支持一下，希望由于

zsmchwszsm

楼主威武了 哦

cqut

xx非常感谢

天行者fl

谢谢分享~~~

wuqiang1123

>> P=[0.511097 0.000000 0.610521 0.703784 0.152057 0.243542 0.528229 0.585062 0.575574 0.846734 0.708163;
      0.245214 0.355971 0.403063 0.536505 0.081968 0.546125 0.778293 0.353942 0.388105 0.711055 0.811224;
      0.096655 0.243478 0.394945 0.000000 0.397686 0.818081 0.667404 0.070539 0.521161 0.326633 0.533673;
      0.170753 0.513043 0.215633 0.082461 0.167467 0.919188 0.742202 0.390041 0.247884 0.898241 0.658163;
      0.417384 0.327536 0.617654 0.326234 0.081782 0.959779 0.648105 1.000000 0.415961 0.940955 0.495918;
      0.278268 0.533333 0.575400 0.038675 0.364196 0.819188 0.910544 0.473029 0.299879 0.572864 0.628571;
      0.195089 0.605797 0.531182 0.073679 0.327506 0.514760 0.000000 0.601660 0.264813 0.859296 0.640816;
      0.621518 0.237681 0.479772 0.546998 0.414864 0.523985 0.742202 0.377593 0.403869 0.591709 0.740816;
      0.454796 0.733333 0.397027 0.078122 0.261989 0.483395 0.856148 0.385892 0.414752 0.396985 0.683673;
      0.385420 0.733333 0.491491 0.007739 0.315568 0.878229 0.922660 0.240664 0.313180 0.531407 0.600000;
      0.354546 0.573913 0.400824 0.185406 0.168788 0.391144 0.631348 0.647303 0.420798 0.728643 0.759184;
      0.359994 0.762319 0.617252 0.013225 0.117663 0.878229 0.844548 0.419087 1.000000 0.863065 0.728571;
      0.261923 1.000000 0.458592 0.136301 0.231462 0.697471 0.631348 0.390041 0.299879 0.565327 0.867347;
      0.375976 0.297275 0.293763 1.000000 0.150754 0.749077 0.502449 0.300830 0.507860 0.716080 0.853061;
      0.590280 0.466667 0.418887 0.723622 0.145586 0.948339 0.729312 0.585062 0.597340 1.000000 0.000000;
      0.321492 0.501449 0.353234 0.102278 0.251131 0.176384 0.842743 0.460996 0.259976 0.909548 0.878571;
      0.393411 0.646377 0.364897 0.042492 0.545196 0.575646 1.000000 0.004149 0.217654 0.781407 0.650000;
      0.435182 0.588406 0.420530 0.099232 0.291452 0.424354 0.763341 0.045643 0.395405 0.858040 0.629592;
      0.346918 0.646377 0.435498 0.223956 0.193329 0.464945 0.579789 0.149378 0.430472 0.796482 0.689796;
      0.236497 0.556522 0.458135 0.019358 0.208913 0.040590 0.399752 0.049793 0.611850 0.806533 0.636735;
      0.278268 0.762319 0.517459 0.206579 0.142947 0.221402 0.811807 0.273029 0.354293 0.772613 0.650000];
T=[3 24 28 36 6 100 41 10 25 32 19 49 11 2 4 16 46 65 7 77 20];
net=newff([0 1;0 1;0 1;0 1;0 1;0 1;0 1;0 1;0 1;0 1;0 1],[13,1],{'tansig','logsig'},'trainlm');
net.trainParam.epochs=10000;net.trainParam.goal=0.01;
LP.lr=0.1;
net=train(net,P',T)
TRAINLM, Epoch 0/10000, MSE 1491.6/0.01, Gradient 432.901/1e-010
TRAINLM, Epoch 3/10000, MSE 1466.1/0.01, Gradient 0/1e-010
TRAINLM, Minimum gradient reached, performance goal was not met.


net =

    Neural Network object:

    architecture:

         numInputs: 1
         numLayers: 2
       biasConnect: [1; 1]
      inputConnect: [1; 0]
      layerConnect: [0 0; 1 0]
     outputConnect: [0 1]
     targetConnect: [0 1]

        numOutputs: 1  (read-only)
        numTargets: 1  (read-only)
    numInputDelays: 0  (read-only)
    numLayerDelays: 0  (read-only)

    subobject structures:

            inputs: {1x1 cell} of inputs
            layers: {2x1 cell} of layers
           outputs: {1x2 cell} containing 1 output
           targets: {1x2 cell} containing 1 target
            biases: {2x1 cell} containing 2 biases
      inputWeights: {2x1 cell} containing 1 input weight
      layerWeights: {2x2 cell} containing 1 layer weight

    functions:

          adaptFcn: 'trains'
           initFcn: 'initlay'
        performFcn: 'mse'
          trainFcn: 'trainlm'

    parameters:

        adaptParam: .passes
         initParam: (none)
      performParam: (none)
        trainParam: .epochs, .goal, .max_fail, .mem_reduc,
                    .min_grad, .mu, .mu_dec, .mu_inc,
                    .mu_max, .show, .time

    weight and bias values:

                IW: {2x1 cell} containing 1 input weight matrix
                LW: {2x2 cell} containing 1 layer weight matrix
                 b: {2x1 cell} containing 2 bias vectors

    other:

          userdata: (user stuff)
求教得到的结果是一条直线，没有达到预定误差，应该怎样设计网络结构？？？？

socute12

学习了！！！！！

中庸

ddddddddddddd

z211211211

不错啊，很实用

socute12

学习了  感谢LZ

z211211211

下载来看看快快快