《神经网络的实例 自由竞争网络的分类识别的matlab编程》由会员分享，可在线阅读，更多相关《神经网络的实例 自由竞争网络的分类识别的matlab编程（4页珍藏版）》请在金锄头文库上搜索。
1、自由竞争网络的分类识别的matlab编程做一个9阶的魔方矩阵，用前7行来构建网络并验证后2列的归类。A=magic(9);B=A(1:6,:);C=A(7:9,:);D=2 14 16 108 21 300 13 100 12;b=B;c=C;d=D;Q=minmax(b);net=newc(Q,2,0.1);net=init(net)net.trainParam.epochs=100;train(net,b)p=sim(net,b)p1=sim(net,c)p2=sim(net,d)运行结果如下： A=magic(9);B=A(1:6,:);C=A(7:9,:);D=2 14 16 108
2、21 300 13 100 12;b=B;c=C;d=D;Q=minmax(b);net=newc(Q,3,0.1);net=init(net)net.trainParam.epochs=100;train(net,b)p=sim(net,b)p1=sim(net,c)p2=sim(net,d)net = Neural Network object: architecture: numInputs: 1 numLayers: 1 biasConnect: 1 inputConnect: 1 layerConnect: 0 outputConnect: 1 targetConnect: 0 nu
3、mOutputs: 1 (read-only) numTargets: 0 (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 targets: 1x1 cell containing no targets biases: 1x1 cell containing 1 bias i
4、nputWeights: 1x1 cell containing 1 input weight layerWeights: 1x1 cell containing no layer weights functions: adaptFcn: trains initFcn: initlay performFcn: (none) trainFcn: trainr parameters: adaptParam: .passes initParam: (none) performParam: (none) trainParam: .epochs, .goal, .show, .time weight a
5、nd 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: userdata: (user stuff)TRAINR, Epoch 0/100TRAINR, Epoch 25/100TRAINR, Epoch 50/100TRAINR, Epoch 75/100TRAINR, Epoch 100/100TRAINR, Maximum epoch r
6、eached.ans = Neural Network object: architecture: numInputs: 1 numLayers: 1 biasConnect: 1 inputConnect: 1 layerConnect: 0 outputConnect: 1 targetConnect: 0 numOutputs: 1 (read-only) numTargets: 0 (read-only) numInputDelays: 0 (read-only) numLayerDelays: 0 (read-only) subobject structures: inputs: 1
7、x1 cell of inputs layers: 1x1 cell of layers outputs: 1x1 cell containing 1 output targets: 1x1 cell containing no targets biases: 1x1 cell containing 1 bias inputWeights: 1x1 cell containing 1 input weight layerWeights: 1x1 cell containing no layer weights functions: adaptFcn: trains initFcn: initl
8、ay performFcn: (none) trainFcn: trainr parameters: adaptParam: .passes initParam: (none) performParam: (none) trainParam: .epochs, .goal, .show, .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: userdata: (user stuff)p = (1,1) 1 (1,2) 1 (1,3) 1 (1,4) 1 (1,5) 1 (1,6) 1p1 = (1,1) 1 (1,2) 1 (1,3) 1p2 = (1,1) 1
