Neural network with multiple inputs and single output - How to improve the performance of neural network?

Question

pepper yuan 2016-4-8

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/277853-neural-network-with-multiple-inputs-and-single-output-how-to-improve-the-performance-of-neural-net

评论： Chris P 2020-8-27

Hello everyone! I would like to create a neural network with 5 input nodes. In the following I have created a simple code with the help of the neural network toolbox. I have a question regarding this code.

How can i improve the performance of network as i use different training algorithm (trainlm and trainscg) with different transfer function(logsig and tansig) in hidden layer, but the best results obtained are only 0.64 MSE and 0.35 R by using trainlm and tansig.

Here is my code:

                  x = rinputs;
                  t = rtargetfourthroot;
                  % Choose a Training Function
                  % For a list of all training functions type: help nntrain
                  % 'trainlm' is usually fastest.
                  % 'trainbr' takes longer but may be better for challenging problems.
                  % 'trainscg' uses less memory. Suitable in low memory situations.
                  trainFcn = 'trainlm';  % Levenberg-Marquardt backpropagation.
                  % Create a Fitting Network
                  hiddenLayerSize = 5;
                  net = fitnet(hiddenLayerSize,trainFcn);
                  % Selection of internal transfer functions
                   net.layers{1}.transferFcn = 'tansig';
                   net.layers{2}.transferFcn = 'purelin';
                  % Choose Input and Output Pre/Post-Processing Functions
                  % For a list of all processing functions type: help nnprocess
                  net.input.processFcns = {'removeconstantrows','mapminmax'};
                  net.output.processFcns = {'removeconstantrows','mapminmax'};
                  % Setup Division of Data for Training, Validation, Testing
                  % For a list of all data division functions type: help nndivide
                  net.divideFcn = 'dividerand';  % Divide data randomly
                  net.divideMode = 'sample';  % Divide up every sample
                  net.divideParam.trainRatio = 60/100;
                  net.divideParam.valRatio = 20/100;
                  net.divideParam.testRatio = 20/100;
                  % Choose a Performance Function
                  % For a list of all performance functions type: help nnperformance
                  net.performFcn = 'mse';  % Mean Squared Error
                  % Choose Plot Functions
                  % For a list of all plot functions type: help nnplot
                  net.plotFcns = {'plotperform','plottrainstate','ploterrhist', ...
                      'plotregression', 'plotfit'};
                  % Train the Network
                  [net,tr] = train(net,x,t);
                  % Test the Network
                  y = net(x);
                  e = gsubtract(t,y);
                  performance = perform(net,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(net,trainTargets,y)
                  valPerformance = perform(net,valTargets,y)
                  testPerformance = perform(net,testTargets,y)