matlab-神经网络-感知器(1)

最新推荐文章于 2023-08-23 21:21:26 发布

deepfuture

最新推荐文章于 2023-08-23 21:21:26 发布

阅读量163

点赞数

分类专栏：数学与计算文章标签： matlab 人工智能

数学与计算专栏收录该内容

434 篇文章 2 订阅

订阅专栏

注意：

空格和","都是数组元素分隔符

[1,2]和[1 2]是同个数组

下面是一个神经元的情况：

>> clear all
>> P=[0 2]

P =

0 2

>> T=[0 1]

T =

0 1

P和T是2个矩阵，

P:R*Q的矩阵，由R组输入向量的最大值和最小值组成

T:S*Q的矩阵，S为神经元个数

>> nte=newp(P,T)

nte =

Neural Network object:

architecture:

         numInputs: 1
         numLayers: 1
       biasConnect: [1]
      inputConnect: [1]
      layerConnect: [0]
     outputConnect: [1]

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

subobject structures:

            inputs: {1x1 cell} of inputs
            layers: {1x1 cell} of layers
           outputs: {1x1 cell} containing 1 output
            biases: {1x1 cell} containing 1 bias
      inputWeights: {1x1 cell} containing 1 input weight
      layerWeights: {1x1 cell} containing no layer weights

functions:

          adaptFcn: 'trains'
         divideFcn: (none)
       gradientFcn: 'calcgrad'
           initFcn: 'initlay'
        performFcn: 'mae'
          plotFcns: {'plotperform','plottrainstate'}
          trainFcn: 'trainc'

parameters:

        adaptParam: .passes
       divideParam: (none)
     gradientParam: (none)
         initParam: (none)
      performParam: (none)
        trainParam: .show, .showWindow, .showCommandLine, .epochs,
                    .goal, .time

weight and bias values:

                IW: {1x1 cell} containing 1 input weight matrix
                LW: {1x1 cell} containing no layer weight matrices
                 b: {1x1 cell} containing 1 bias vector

other:

权值

>> w1=nte.iw{1}

w1 =

阈值

>> w1=nte.b{1}

w1 =

>> nte.iw{1,1}=7

nte =

Neural Network object:

architecture:

         numInputs: 1
         numLayers: 1
       biasConnect: [1]
      inputConnect: [1]
      layerConnect: [0]
     outputConnect: [1]

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

subobject structures:

functions:

parameters:

weight and bias values:

                IW: {1x1 cell} containing 1 input weight matrix
                LW: {1x1 cell} containing no layer weight matrices
                 b: {1x1 cell} containing 1 bias vector

other:

>> w1=nte.b{1}

w1 =

>> nte.b{1}=8

nte =

Neural Network object:

architecture:

         numInputs: 1
         numLayers: 1
       biasConnect: [1]
      inputConnect: [1]
      layerConnect: [0]
     outputConnect: [1]

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

subobject structures:

functions:

parameters:

weight and bias values:

                IW: {1x1 cell} containing 1 input weight matrix
                LW: {1x1 cell} containing no layer weight matrices
                 b: {1x1 cell} containing 1 bias vector

other:

>> b=nte.b{1}

b =

初始化网络

>> nte=init(nte)

nte =

Neural Network object:

architecture:

         numInputs: 1
         numLayers: 1
       biasConnect: [1]
      inputConnect: [1]
      layerConnect: [0]
     outputConnect: [1]

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

subobject structures:

functions:

parameters:

weight and bias values:

                IW: {1x1 cell} containing 1 input weight matrix
                LW: {1x1 cell} containing no layer weight matrices
                 b: {1x1 cell} containing 1 bias vector

other:

>> nte.iw{1}

ans =

>> nte.b{1}

ans =

随机数为权值和阈值

>> clear all
>> net=newp([0 1;-2 2],1)

net =

Neural Network object:

architecture:

         numInputs: 1
         numLayers: 1
       biasConnect: [1]
      inputConnect: [1]
      layerConnect: [0]
     outputConnect: [1]

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

subobject structures:

functions:

parameters:

weight and bias values:

                IW: {1x1 cell} containing 1 input weight matrix
                LW: {1x1 cell} containing no layer weight matrices
                 b: {1x1 cell} containing 1 bias vector

other:

>> net.inputweights{1,1}.initFcn='rands'

net =

Neural Network object:

architecture:

         numInputs: 1
         numLayers: 1
       biasConnect: [1]
      inputConnect: [1]
      layerConnect: [0]
     outputConnect: [1]

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

subobject structures:

functions:

parameters:

weight and bias values:

                IW: {1x1 cell} containing 1 input weight matrix
                LW: {1x1 cell} containing no layer weight matrices
                 b: {1x1 cell} containing 1 bias vector

other:

>> net.biases{1}.initFcn='rands'

net =

Neural Network object:

architecture:

         numInputs: 1
         numLayers: 1
       biasConnect: [1]
      inputConnect: [1]
      layerConnect: [0]
     outputConnect: [1]

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

subobject structures:

functions:

parameters:

weight and bias values:

                IW: {1x1 cell} containing 1 input weight matrix
                LW: {1x1 cell} containing no layer weight matrices
                 b: {1x1 cell} containing 1 bias vector

other:

>> net=init(net)

net =

Neural Network object:

architecture:

         numInputs: 1
         numLayers: 1
       biasConnect: [1]
      inputConnect: [1]
      layerConnect: [0]
     outputConnect: [1]

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

subobject structures:

functions:

parameters:

weight and bias values:

                IW: {1x1 cell} containing 1 input weight matrix
                LW: {1x1 cell} containing no layer weight matrices
                 b: {1x1 cell} containing 1 bias vector

other:

>> net.iw{1,1}

ans =

0.8116 -0.7460

>> net.b{1}

ans =

0.6294