Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
NPM :17351197
BACKPROPAGATION (KCB)
>> p=[0.25 0.25 0.5 0.5 0.5 0.75 0.75 0.75 0.5 0.5;60 80 70 70 70 70 70 70 70 70;65 70 80 80 80 70 90 70
80 80;1 0 1 1 0 1 0 1 0 1];
> In nntobsu at 18
In newff at 86
See help for NEWFF to update calls to the new argument list.
>> net.IW{1,1}
ans =
>> net.b{1}
ans =
-9.4560
-6.6895
-13.9707
-3.1408
11.0090
-16.1588
>> net.LW{2,1}
ans =
>> net.b{2}
ans =
-3.3626
3.3626
>> [a,Pf,Af,e,Perf]=sim(net,p,[],[],t)
a=
Columns 1 through 8
Columns 9 through 10
0.0290 0.6324
0.0315 0.1525
0.9933 0.9313
Pf =
[]
Af =
[]
e=
Columns 1 through 8
Columns 9 through 10
0.9710 -0.6324
-0.0315 0.8475
-0.9933 -0.9313
Perf =
0.6303
>> net.trainParam.show=500;
>> net.trainParam.goal=0.01;
>> net=train(net,p,t)
net =
architecture:
numInputs: 1
numLayers: 2
biasConnect: [1; 1]
inputConnect: [1; 0]
layerConnect: [0 0; 1 0]
outputConnect: [0 1]
numOutputs: 1 (read-only)
numInputDelays: 0 (read-only)
numLayerDelays: 0 (read-only)
subobject structures:
adaptFcn: 'trains'
divideFcn: (none)
gradientFcn: 'calcgrad'
initFcn: 'initlay'
performFcn: 'mse'
plotFcns: {'plotperform','plottrainstate','plotregression'}
trainFcn: 'traingdx'
parameters:
adaptParam: .passes
divideParam: (none)
gradientParam: (none)
initParam: (none)
performParam: (none)
.min_grad
other:
name: ''
>> [a,Pf,Af,e,Perf]=sim(net,p,[],[],t)
a=
Columns 1 through 8
Columns 9 through 10
0.8507 0.1590
0.1208 0.8751
0.0090 0.0485
Pf =
[]
Af =
[]
e=
Columns 1 through 8
Columns 9 through 10
0.1493 -0.1590
-0.1208 0.1249
-0.0090 -0.0485
Perf =
0.0100
>> a'
ans =
>>
>>