matlab 代码标准格式,（已修改为标准格式，有代码）BP神经网络中遇到的几个问题...

[Pn,ps]=mapminmax(P)

Pn =

-1.0000   -0.9007   -0.7955   -0.6568   -0.4551   -0.2711   -0.0440    0.2123    0.5153    1.0000

-1.0000   -0.8773   -0.6534   -0.5307   -0.2455   -0.0108    0.3935    0.6534    0.9025    1.0000

ps =

name: 'mapminmax'

xrows: 2

xmax: [2x1 double]

xmin: [2x1 double]

xrange: [2x1 double]

yrows: 2

ymax: 1

ymin: -1

yrange: 2

no_change: 0

gain: [2x1 double]

xoffset: [2x1 double]

>> [Tn,ts]=mapminmax(T)

Tn =

-1.0000   -0.9348   -0.8913   -0.8043   -0.6087   -0.3696   -0.1087    0.1304    0.5217    1.0000

ts =

name: 'mapminmax'

xrows: 1

xmax: 16.1000

xmin: 6.9000

xrange: 9.2000

yrows: 1

ymax: 1

ymin: -1

yrange: 2

no_change: 0

gain: 0.2174

xoffset: 6.9000

net=newff(Pn,Tn,9,{'tansig','purelin'},'trainlm')

net =

Neural Network

name: 'Custom Neural Network'

userdata: (your custom info)

dimensions:

numInputs: 1

numLayers: 2

numOutputs: 1

numInputDelays: 0

numLayerDelays: 0

numFeedbackDelays: 0

numWeightElements: 37

sampleTime: 1

connections:

biasConnect: [1; 1]

inputConnect: [1; 0]

layerConnect: [0 0; 1 0]

outputConnect: [0 1]

subobjects:

input: Equivalent to inputs{1}

output: Equivalent to outputs{2}

inputs: {1x1 cell array of 1 input}

layers: {2x1 cell array of 2 layers}

outputs: {1x2 cell array of 1 output}

biases: {2x1 cell array of 2 biases}

inputWeights: {2x1 cell array of 1 weight}

layerWeights: {2x2 cell array of 1 weight}

functions:

adaptFcn: 'adaptwb'

adaptParam: (none)

derivFcn: 'defaultderiv'

divideFcn: 'dividerand'

divideParam: .trainRatio, .valRatio, .testRatio

divideMode: 'sample'

initFcn: 'initlay'

performFcn: 'mse'

performParam: .regularization, .normalization

plotFcns: {'plotperform', plottrainstate,

plotregression}

plotParams: {1x3 cell array of 3 params}

trainFcn: 'trainlm'

trainParam: .showWindow, .showCommandLine, .show, .epochs,

.time, .goal, .min_grad, .max_fail, .mu, .mu_dec,

.mu_inc, .mu_max

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

methods:

adapt: Learn while in continuous use

configure: Configure inputs & outputs

gensim: Generate Simulink model

init: Initialize weights & biases

perform: Calculate performance

sim: Evaluate network outputs given inputs

train: Train network with examples

view: View diagram

unconfigure: Unconfigure inputs & outputs

evaluate:       outputs = net(inputs)

net.trainParam.show=50;

net.trainParam.lr=0.01;

net.trainParam.mc=0.9;

net.trainParam.epochs=100000;

net.trainParam.goal=0.01;

>> [net,tr]=train(net,Pn,Tn)

net =

Neural Network

name: 'Custom Neural Network'

userdata: (your custom info)

dimensions:

numInputs: 1

numLayers: 2

numOutputs: 1

numInputDelays: 0

numLayerDelays: 0

numFeedbackDelays: 0

numWeightElements: 37

sampleTime: 1

connections:

biasConnect: [1; 1]

inputConnect: [1; 0]

layerConnect: [0 0; 1 0]

outputConnect: [0 1]

subobjects:

input: Equivalent to inputs{1}

output: Equivalent to outputs{2}

inputs: {1x1 cell array of 1 input}

layers: {2x1 cell array of 2 layers}

outputs: {1x2 cell array of 1 output}

biases: {2x1 cell array of 2 biases}

inputWeights: {2x1 cell array of 1 weight}

layerWeights: {2x2 cell array of 1 weight}

functions:

adaptFcn: 'adaptwb'

adaptParam: (none)

derivFcn: 'defaultderiv'

divideFcn: 'dividerand'

divideParam: .trainRatio, .valRatio, .testRatio

divideMode: 'sample'

initFcn: 'initlay'

performFcn: 'mse'

performParam: .regularization, .normalization

plotFcns: {'plotperform', plottrainstate,

plotregression}

plotParams: {1x3 cell array of 3 params}

trainFcn: 'trainlm'

trainParam: .showWindow, .showCommandLine, .show, .epochs,

.time, .goal, .min_grad, .max_fail, .mu, .mu_dec,

.mu_inc, .mu_max, .lr, .mc

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

methods:

adapt: Learn while in continuous use

configure: Configure inputs & outputs

gensim: Generate Simulink model

init: Initialize weights & biases

perform: Calculate performance

sim: Evaluate network outputs given inputs

train: Train network with examples

view: View diagram

unconfigure: Unconfigure inputs & outputs

evaluate:       outputs = net(inputs)

tr =

trainFcn: 'trainlm'

trainParam: [1x1 struct]

performFcn: 'mse'

performParam: [1x1 struct]

derivFcn: 'defaultderiv'

divideFcn: 'dividerand'

divideMode: 'sample'

divideParam: [1x1 struct]

trainInd: [1 2 4 5 6 7 9 10]

valInd: 8

testInd: 3

stop: 'Performance goal met.'

num_epochs: 3

trainMask: {[1 1 NaN 1 1 1 1 NaN 1 1]}

valMask: {[NaN NaN NaN NaN NaN NaN NaN 1 NaN NaN]}

testMask: {[NaN NaN 1 NaN NaN NaN NaN NaN NaN NaN]}

best_epoch: 2

goal: 0.0100

states: {'epoch'  'time'  'perf'  'vperf'  'tperf'  'mu'  'gradient'  'val_fail'}

epoch: [0 1 2 3]

time: [0.3110 0.4370 0.4510 0.4580]

perf: [4.8979 0.0847 0.0106 6.2624e-04]

vperf: [1.2198 0.6976 9.1008e-05 0.0354]

tperf: [1.5746 0.0850 6.7547e-06 8.7878e-06]

mu: [1.0000e-03 1.0000e-04 1.0000e-05 1.0000e-06]

gradient: [8.3152 0.8621 0.2466 0.0739]

val_fail: [0 0 0 1]

best_perf: 0.0106

best_vperf: 9.1008e-05

best_tperf: 6.7547e-06