p2 =

  Columns 1 through 15

   10.3547    6.5132   11.5884    9.0937   12.1231    9.7305    9.2718   12.0138   14.7256    8.2118   15.5248    9.4856    7.0331    8.2986   15.1273
    9.5938   21.5208    8.5775    9.7130    8.4882    8.6062    9.3576    8.3573    6.9854   11.4787    7.2933    8.6076   15.5258   12.4651    7.0822

  Columns 16 through 30

   14.8087   23.6421    6.0581   20.4587    7.1942   23.8723    9.0817   11.5870    7.7996   25.0767    7.5711   18.7319    6.9550    8.0761    8.8435
    7.2593    6.2705   23.3829    6.5035   15.9076    6.2138   10.2243    8.7950   13.2521    6.2182   14.6978    6.5399   17.7876   12.9900   10.7082

  Columns 31 through 33

   10.6579    6.0759   20.5206
    8.3639   24.7947    6.5797



t2 =

  Columns 1 through 15

   49.5501   90.0034   20.8415   61.8249    9.7315   67.7766   75.0265   90.8393   18.4378   25.9050   73.1686   34.7021   27.0085   26.0106   23.0541
   84.8077   87.6767   74.2318   85.1866   34.1156   94.6325   18.0468   74.0764   43.0147   18.5151   59.4235   52.3822    8.8075   20.4177   51.2638

  Columns 16 through 30

   18.9169   72.0445   78.1773   32.3433    0.6327   91.9820   68.5819   40.0343   76.3430   69.6676   60.1632   62.4337   20.0080   66.1757   85.5082
    3.1980   99.4590   38.8818    9.3058   76.9212   50.6772   25.3198   24.3151   79.0716   61.9660   26.6020   61.0964   67.1891   80.4363   31.2752

  Columns 31 through 33

   51.8444   48.1827   82.4095
   34.3136   39.1259   59.6381



net2=newff([0 100],[500,2],{'logsig','purelin'},'traincgf');



net2 =

    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'
       gradientFcn: 'calcgrad'
           initFcn: 'initlay'
        performFcn: 'mse'
          trainFcn: 'traincgf'

    parameters:

        adaptParam: .passes
     gradientParam: (none)
         initParam: (none)
      performParam: (none)
        trainParam: .epochs, .show, .goal, .time,
                    .min_grad, .max_fail, .searchFcn, .scale_tol,
                    .alpha, .beta, .delta, .gama,
                    .low_lim, .up_lim, .maxstep, .minstep,
                    .bmax

    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 information)



NN2=train(net2,p2,t2)
??? Error using ==> network.train at 228
Inputs are incorrectly sized for network.
Matrix must have 1 rows.



请问，为什么我的程序会报这样的错误呢？？