How to calculate accuracy for neural network algorithms?

How to calculate accuracy for neural network algorithms?

[Adam]

I'm pretty sure this is a topic with literally thousands of hits if you google it! Or are you asking specifically about a Matlab coded network, in which case showing some code helps.

Answer 1

[Greg Heath]

I normalize the mean-square-error

MSE = mse(error) = mse(output-target)

by the minimum MSE obtained when the output is a constant.

If the output is a constant, the MSE is minimized when that constant is

the average of the target. For a 1-D target

NMSE = mse(output-target) / mse(target-mean(target))

= mse(error) / var(target,1)

This is related to the R-square statistic (AKA as R2) via

Rsquare = R2 = 1 - NMSE

Both NMSE and R2 are contained in [0,1].

I have posted zillions of examples in both the NEWSGROUP and ANSWERS.

Just search using

Greg NMSE

Thank you for formally accepting my answer

Greg

[sandhya sandhya]

Thank you sir :)

[sandhya sandhya]

Hi sir,i tried below code and i want to calculate the accuracy for this code.please help me if possible

input=load('project1.mat'); %420 x 24

target=load('braineeg.mat'); %1 x 420

hiddenLayerSize = 10;

net = feedforwardnet(hiddenLayerSize );

net.divideFcn = 'divideind';

net.divideParam.trainInd = 1:1792;

net.divideParam.valInd = 1793:2176;

net.divideParam.testInd = 2177:2560;

% [net,tr] = train(net,input,target);

[net,tr] = train(net,input.val,target.val);

view(net)

output = net(input.val);

errors = gsubtract(target.val,output);

performance = perform(net,target.val,output);

figure, plotperform(tr)

figure, plottrainstate(tr)

figure, plotconfusion(target.val,output)

[c,cm] = confusion(target.val,output);

fprintf('Percentage Correct Classification : %f%%\n', 100*(1-c));

fprintf('Percentage Incorrect Classification : %f%%\n', 100*c);

figure, ploterrhist(errors)

trainTargets = target.val .* tr.trainMask{1};

valTargets = target.val .* tr.valMask{1};

testTargets = target.val .* tr.testMask{1};

trainPerformance = perform(net,trainTargets,output);

valPerformance = perform(net,valTargets,output);

testPerformance = perform(net,testTargets,output);

MSE = mse(error) = mse(output-target)

[Greg Heath]

Your numbers make no sense

1. A 1x420 target requires the input to be transposed
2. Where does 2560 come from???
3. Your use of *.val makes no sense

[sandhya sandhya]

Input signal with dimension 1*420 was my previous signal ,I forgot to modify the dimension.Now,the input signal with dimension 23*2560 and *.val is the inbuilt file of input signal.If you give command as plot(input),it displays the error.But ,if you give command as

plot(input.val), then it displays the output.Can you please add accuracy commands to my code.

input=load('project1.mat'); 23*2560

target=load('braineeg.mat');

hiddenLayerSize = 10;

net = feedforwardnet(hiddenLayerSize );

net.divideFcn = 'divideind';

net.divideParam.trainInd = 1:1792;

net.divideParam.valInd = 1793:2176;

net.divideParam.testInd = 2177:2560;

net = configure(net,input.val,target.val);

[net,tr] = train(net,input.val,target.val);

view(net)

output = net(input.val);

errors = gsubtract(target.val,output);

performance = perform(net,target.val,output);

view(net)

figure, plotperform(tr)

figure, plottrainstate(tr)

figure, plotconfusion(target.val,output)

[c,cm] = confusion(target.val,output);

figure, ploterrhist(errors)

trainTargets = target.val .* tr.trainMask{1};

valTargets = target.val .* tr.valMask{1};

testTargets = target.val .* tr.testMask{1};

trainPerformance = perform(net,trainTargets,output);

valPerformance = perform(net,valTargets,output);

testPerformance = perform(net,testTargets,output);

YPred = predict(net,input.val);

MSE=mse(output-target.val);

NMSE = MSE / mse(target-mean(target.val));

[Osama Tabbakh]

But what I do not understand is in the way of R-square statistic you calculate with the consideration that the behavior between the target and the output is linear. But when the behavior is nonlinear, then you get high accuracy, although the network produces a large error.