资源描述：
《神经网络的实例 自由竞争网络的分类识别的matlab编程》由会员上传分享，免费在线阅读，更多相关内容在工程资料-天天文库。
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=[21416108213001310012];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：>>
2、A=magic(9);B=A(1:6,:);C=A(7:9,:);D=[21416108213001310012];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=NeuralNetworkobject:architecture:numInputs:1numLayers:1
3、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)subobjectstructures:inputs:{1x1cell}ofinputslayers:{1x1cell}oflayersou
4、tputs:{1x1cell}containing1outputtargets:{1x1cell}containingnotargetsbiases:{1x1cell}containing1biasinputWeights:{1x1cell}containing1inputweightlayerWeights:{1x1cell}containingnolayerweightsfunctions:adaptFcn:'trains'initFcn:'initlay'performFcn:(none)t
5、rainFcn:'trainr'parameters:adaptParam:.passesinitParam:(none)performParam:(none)trainParam:.epochs,.goal,.show,.timeweightandbiasvalues:IW:{1x1cell}containing1inputweightmatrixLW:{1x1cell}containingnolayerweightmatricesb:{1x1cell}containing1biasvector
6、other:userdata:(userstuff)TRAINR,Epoch0/100TRAINR,Epoch25/100TRAINR,Epoch50/100TRAINR,Epoch75/100TRAINR,Epoch100/100TRAINR,Maximumepochreached.ans=NeuralNetworkobject:architecture:numInputs:1numLayers:1biasConnect:[1]inputConnect:[1]layerConnect:[0]ou
7、tputConnect:[1]targetConnect:[0]numOutputs:1(read-only)numTargets:0(read-only)numInputDelays:0(read-only)numLayerDelays:0(read-only)subobjectstructures:inputs:{1x1cell}ofinputslayers:{1x1cell}oflayersoutputs:{1x1cell}containing1outputtargets:{1x1cell}
8、containingnotargetsbiases:{1x1cell}containing1biasinputWeights:{1x1cell}containing1inputweightlayerWeights:{1x1cell}containingnolayerweightsfunctions:adaptFcn:'trains'initFcn:'initlay'performFcn:(none)trainFcn:'trainr'parameters:adaptParam:.pa
