目录
1 分解代码
1.1 循环准备1.2 神经网络构建1.3 数据处置1.4 模型训练参数配置1.5 神经网络实现1.6 精度衡量1.7 保管模型
2 完好代码
在之前的文章MATLAB实现随机森林(RF)回归与自变量影响水平分析中,我们对基于MATLAB的随机森林(RF)回归与变量影响水平(重要性)排序的代码加以详细讲解与理论。本次我们继续基于MATLAB,对另一种常用的机器学习方法——神经网络方法加以代码实战。
首先需要注明的是,在MATLAB中,我们可以直接基于“APP”中的“Neural Net Fitting”工具箱实如今无需代码的情况下,对神经网络算法加以运行。
基于工具箱的神经网络方法虽然方便,但是一些参数不能调整;同时也不利于我们对算法、代码的理解。因而,本文不利用“Neural Net Fitting”工具箱,而是直接通过代码将神经网络方法加以运行——但是,本文的代码其实也是通过上述工具箱运行后生成的;而这种生成神经网络代码的方法也是MATLAB官方推荐的方式。
另外,需要注意的是,本文直接停止神经网络算法的执行,省略了前期数据处置、训练集与测试集划分、精度衡量指标选取等。因而建议大家先将文章MATLAB实现随机森林(RF)回归与自变量影响水平分析阅读后,再阅读本文。
本文分为两部分,首先是将代码分段、详细讲解,方便大家理解;随后是完好代码,方便大家自行尝试。
1 分解代码
1.1 循环准备
由于机器学习往往需要屡次执行,我们就在此先定义循环。- %% ANN Cycle Preparation
- ANNRMSE=9999;
- ANNRunNum=0;
- ANNRMSEMatrix=[];
- ANNrAllMatrix=[];
- while ANNRMSE>400
复制代码 其中,ANNRMSE是初始的RMSE;ANNRunNum是神经网络算法当前运行的次数;ANNRMSEMatrix用来存储每一次神经网络运行后所得到的RMSE结果;ANNrAllMatrix用来存储每一次神经网络运行后所得到的皮尔逊相关系数结果;最后一句表示当所得到的模型RMSE>400时,则停止循环。
1.2 神经网络构建
接下来,我们对神经网络的整体构造加以定义。- %% ANN
- x=TrainVARI';
- t=TrainYield';
- trainFcn = 'trainlm';
- hiddenLayerSize = [10 10 10];
- ANNnet = fitnet(hiddenLayerSize,trainFcn);
复制代码 其中,TrainVARI、TrainYield分别是我这里训练数据的自变量(特征)与因变量(标签);trainFcn为神经网络所选用的训练函数方法名称,其名称与对应的方法对照如下表:
hiddenLayerSize为神经网络所用隐层与各层神经元个数,[10 10 10]代表共有三层隐层,各层神经元个数分别为10,10与10。
1.3 数据处置
接下来,对输入神经网络模型的数据加以处置。- ANNnet.input.processFcns = {'removeconstantrows','mapminmax'};
- ANNnet.output.processFcns = {'removeconstantrows','mapminmax'};
- ANNnet.divideFcn = 'dividerand';
- ANNnet.divideMode = 'sample';
- ANNnet.divideParam.trainRatio = 0.6;
- ANNnet.divideParam.valRatio = 0.4;
- ANNnet.divideParam.testRatio = 0.0;
复制代码 其中,ANNnet.input.processFcns与ANNnet.output.processFcns分别代表输入模型数据的处置方法,'removeconstantrows'表示删除在各样本中数值始终一致的特征列,'mapminmax'表示将数据归一化处置;divideFcn表示划分数据训练集、验证集与测试集的方法,'dividerand'表示根据所给定的比例随机划分;divideMode表示对数据划分的维度,我们这里选择'sample',也就是对样本停止划分;divideParam表示训练集、验证集与测试集所占比例,那么在这里,因为是直接用了先前随机森林方法(可以看这篇博客)中的数据划分方式,那么为了保证训练集、测试集的固定,我们就将divideParam.testRatio设置为0.0,然后将训练集与验证集比例划分为0.6与0.4。
1.4 模型训练参数配置
接下来对模型运行过程中的主要参数加以配置。- ANNnet.performFcn = 'mse';
- ANNnet.trainParam.epochs=5000;
- ANNnet.trainParam.goal=0.01;
复制代码 其中,performFcn为模型误差衡量函数,'mse'表示均方误差;trainParam.epochs表示训练时Epoch次数,trainParam.goal表示模型所要到达的精度要求(即模型运行到trainParam.epochs次时或误差小于trainParam.goal时将会停止运行)。
1.5 神经网络实现
这一部分代码大多数与绘图、代码与GUI生成等相关,因而就不再逐个解释了,大家可以直接运行。需要注意的是,train是模型训练函数。- % For a list of all plot functions type: help nnplot
- ANNnet.plotFcns = {'plotperform','plottrainstate','ploterrhist','plotregression','plotfit'};
- [ANNnet,tr] = train(ANNnet,x,t);
- y = ANNnet(x);
- e = gsubtract(t,y);
- performance = perform(ANNnet,t,y);
- % Recalculate Training, Validation and Test Performance
- trainTargets = t .* tr.trainMask{1};
- valTargets = t .* tr.valMask{1};
- testTargets = t .* tr.testMask{1};
- trainPerformance = perform(ANNnet,trainTargets,y);
- valPerformance = perform(ANNnet,valTargets,y);
- testPerformance = perform(ANNnet,testTargets,y);
- % view(net)
- % Plots
- %figure, plotperform(tr)
- %figure, plottrainstate(tr)
- %figure, ploterrhist(e)
- %figure, plotregression(t,y)
- %figure, plotfit(net,x,t)
- % Deployment
- % See the help for each generation function for more information.
- if (false)
- % Generate MATLAB function for neural network for application
- % deployment in MATLAB scripts or with MATLAB Compiler and Builder
- % tools, or simply to examine the calculations your trained neural
- % network performs.
- genFunction(ANNnet,'myNeuralNetworkFunction');
- y = myNeuralNetworkFunction(x);
- end
- if (false)
- % Generate a matrix-only MATLAB function for neural network code
- % generation with MATLAB Coder tools.
- genFunction(ANNnet,'myNeuralNetworkFunction','MatrixOnly','yes');
- y = myNeuralNetworkFunction(x);
- end
- if (false)
- % Generate a Simulink diagram for simulation or deployment with.
- % Simulink Coder tools.
- gensim(ANNnet);
- end
复制代码 1.6 精度衡量
- %% Accuracy of ANN
- ANNPredictYield=sim(ANNnet,TestVARI')';
- ANNRMSE=sqrt(sum(sum((ANNPredictYield-TestYield).^2))/size(TestYield,1));
- ANNrMatrix=corrcoef(ANNPredictYield,TestYield);
- ANNr=ANNrMatrix(1,2);
- ANNRunNum=ANNRunNum+1;
- ANNRMSEMatrix=[ANNRMSEMatrix,ANNRMSE];
- ANNrAllMatrix=[ANNrAllMatrix,ANNr];
- disp(ANNRunNum);
- end
- disp(ANNRMSE);
复制代码 其中,ANNPredictYield为预测结果;ANNRMSE、ANNrMatrix分别为模型精度衡量指标RMSE与皮尔逊相关系数。结合本文1.1部分可知,我这里设置为当所得神经网络模型RMSE在400以内时,将会停止循环;否则继续开端执行本文1.2部分至1.6部分的代码。
1.7 保管模型
这一部分就不再赘述了,大家可以参考文章MATLAB实现随机森林(RF)回归与自变量影响水平分析。- %% ANN Model Storage
- ANNModelSavePath='G:\CropYield\02_CodeAndMap\00_SavedModel\';
- save(sprintf('%sRF0417ANN0399.mat',ANNModelSavePath),'TestVARI','TestYield','TrainVARI','TrainYield','ANNnet','ANNPredictYield','ANNr','ANNRMSE',...
- 'hiddenLayerSize');
复制代码 2 完好代码
完好代码如下:- %% ANN Cycle Preparation
- ANNRMSE=9999;
- ANNRunNum=0;
- ANNRMSEMatrix=[];
- ANNrAllMatrix=[];
- while ANNRMSE>1000
- %% ANN
- x=TrainVARI';
- t=TrainYield';
- trainFcn = 'trainlm';
- hiddenLayerSize = [10 10 10];
- ANNnet = fitnet(hiddenLayerSize,trainFcn);
- ANNnet.input.processFcns = {'removeconstantrows','mapminmax'};
- ANNnet.output.processFcns = {'removeconstantrows','mapminmax'};
- ANNnet.divideFcn = 'dividerand';
- ANNnet.divideMode = 'sample';
- ANNnet.divideParam.trainRatio = 0.6;
- ANNnet.divideParam.valRatio = 0.4;
- ANNnet.divideParam.testRatio = 0.0;
- ANNnet.performFcn = 'mse';
- ANNnet.trainParam.epochs=5000;
- ANNnet.trainParam.goal=0.01;
- % For a list of all plot functions type: help nnplot
- ANNnet.plotFcns = {'plotperform','plottrainstate','ploterrhist','plotregression','plotfit'};
- [ANNnet,tr] = train(ANNnet,x,t);
- y = ANNnet(x);
- e = gsubtract(t,y);
- performance = perform(ANNnet,t,y);
- % Recalculate Training, Validation and Test Performance
- trainTargets = t .* tr.trainMask{1};
- valTargets = t .* tr.valMask{1};
- testTargets = t .* tr.testMask{1};
- trainPerformance = perform(ANNnet,trainTargets,y);
- valPerformance = perform(ANNnet,valTargets,y);
- testPerformance = perform(ANNnet,testTargets,y);
- % view(net)
- % Plots
- %figure, plotperform(tr)
- %figure, plottrainstate(tr)
- %figure, ploterrhist(e)
- %figure, plotregression(t,y)
- %figure, plotfit(net,x,t)
- % Deployment
- % See the help for each generation function for more information.
- if (false)
- % Generate MATLAB function for neural network for application
- % deployment in MATLAB scripts or with MATLAB Compiler and Builder
- % tools, or simply to examine the calculations your trained neural
- % network performs.
- genFunction(ANNnet,'myNeuralNetworkFunction');
- y = myNeuralNetworkFunction(x);
- end
- if (false)
- % Generate a matrix-only MATLAB function for neural network code
- % generation with MATLAB Coder tools.
- genFunction(ANNnet,'myNeuralNetworkFunction','MatrixOnly','yes');
- y = myNeuralNetworkFunction(x);
- end
- if (false)
- % Generate a Simulink diagram for simulation or deployment with.
- % Simulink Coder tools.
- gensim(ANNnet);
- end
- %% Accuracy of ANN
- ANNPredictYield=sim(ANNnet,TestVARI')';
- ANNRMSE=sqrt(sum(sum((ANNPredictYield-TestYield).^2))/size(TestYield,1));
- ANNrMatrix=corrcoef(ANNPredictYield,TestYield);
- ANNr=ANNrMatrix(1,2);
- ANNRunNum=ANNRunNum+1;
- ANNRMSEMatrix=[ANNRMSEMatrix,ANNRMSE];
- ANNrAllMatrix=[ANNrAllMatrix,ANNr];
- disp(ANNRunNum);
- end
- disp(ANNRMSE);
- %% ANN Model Storage
- ANNModelSavePath='G:\CropYield\02_CodeAndMap\00_SavedModel\';
- save(sprintf('%sRF0417ANN0399.mat',ANNModelSavePath),'AreaPercent','InputOutput','nLeaf','nTree',...
- 'RandomNumber','RFModel','RFPredictConfidenceInterval','RFPredictYield','RFr','RFRMSE',...
- 'TestVARI','TestYield','TrainVARI','TrainYield','ANNnet','ANNPredictYield','ANNr','ANNRMSE',...
- 'hiddenLayerSize');
复制代码 以上就是基于Matlab实现人工神经网络(ANN)回归的示例详解的详细内容,更多关于Matlab人工神经网络ANN回归的资料请关注网站其它相关文章! |