What is the reason of getting high MSE even with data normalization?

Question

Avanthi Saumyamala 2018-10-19

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/424892-what-is-the-reason-of-getting-high-mse-even-with-data-normalization

回答： Ameen Bassam 2022-6-24

Im forecasting solar radiation using 9 input parameters.I have fitted NARX neural network but obtained very high MSE values.My input data are in different ranges and consist of many outliers..Hence the mapminmax normalization or mapstd normalization does not help me in improving the performance.How can I improve the performance of the neural network?

inputSeries = tonndata(Input,false,false); targetSeries = tonndata(Target,false,false);

% Create a Nonlinear Autoregressive Network with External Input

inputDelays = 1:2; feedbackDelays = 1:2; hiddenLayerSize = 10; net = narxnet(inputDelays,feedbackDelays,hiddenLayerSize);

% Choose Input and Feedback Pre/Post-Processing Functions

net.inputs{1}.processFcns = {'removeconstantrows','mapstd'}; net.inputs{2}.processFcns = {'removeconstantrows','mapstd'};

% Prepare the Data for Training and Simulation

[inputs,inputStates,layerStates,targets] = preparets(net,inputSeries,{},targetSeries);

% Setup Division of Data for Training, Validation, Testing

net.divideMode = 'value'; % Divide up every value

net.divideParam.trainRatio = 70/100; net.divideParam.valRatio = 15/100; net.divideParam.testRatio = 15/100;

% Choose a Training Function

net.trainFcn = 'trainlm'; % Levenberg-Marquardt

% Choose a Performance Function

net.performFcn = 'mse'; % Mean squared error

% Choose Plot Functions

net.plotFcns = {'plotperform','plottrainstate','plotresponse', ... 'ploterrcorr', 'plotinerrcorr'};

net.trainParam.max_fail=6;

% Train the Network

[net,tr] = train(net,inputs,targets,inputStates,layerStates);

% Test the Network

outputs = net(inputs,inputStates,layerStates); errors = gsubtract(targets,outputs); performance = perform(net,targets,outputs)

% Recalculate Training, Validation and Test Performance

trainTargets = gmultiply(targets,tr.trainMask); valTargets = gmultiply(targets,tr.valMask); testTargets = gmultiply(targets,tr.testMask); trainPerformance = perform(net,trainTargets,outputs) valPerformance = perform(net,valTargets,outputs) testPerformance = perform(net,testTargets,outputs)

output

performance = 3.6894e+03 trainPerformance = 3.4999e+03 valPerformance = 4.1116e+03 testPerformance = 4.1513e+03 closedLoopPerformance = 3.8351e+03 earlyPredictPerformance = 3.6894e+03