MATLAB: How to change the performance function of neural network to mean absolute relative error

custom performance functionDeep Learning Toolboxmean absolute relative errorneural networks

Hello,

I know the Matlab NN toolbox has MSE, SSE, MAE and SAE performance functions but would like to implement a custom performance function as:

myperf=mean(abs((t-y)./t));

where t is the target output vector and y is the NN output.

Any thoughts on how can this be implemented?

Thanks in advance.

Best Answer

I found my own answer for the performance function myperf = mse(1-y./t) as follows:

net.performFcn='mse'; % this is the default setting

net= train(net,x,t,{},{},1./t); % x is the input matrix.

Note: As pointed out by Greg, t is assumed to have nonzero values.

Related Solutions

MATLAB: MAPE for out-of-sample in neural network

Not sure why you would use a measure that has the possibility of being infinite. However

mape = mean(abs(e./t))

Hope this helps

Thank you for formally accepting my answer

Greg

MATLAB: Test, train and validation performance are so different from global performance in the neural network

As per my knowledge, the way you are calculating the trainPerformance, valPerformance & testPerformance may not be correct. Instead I would suggest that you can make use of tr.trainInd, tr.valInd & tr.testInd instead of tr.trainMask, tr.valMask & tr.testMask as follows:

trainPerformance = perform(net,t(tr.trainInd),y(tr.trainInd))
valPerformance = perform(net,t(tr.testInd),y(tr.testInd))
testPerformance = perform(net,t(tr.valInd),y(tr.valInd))

Then w.r.t performance function, according to your above code the performance function you are using is 'crossentropy' and hence perform(net,t,y,ew) returns network performance calculated according to the net.performFcn which is 'crossentropy' & not 'mse'.

Also for your additional part, you may have to use

trp = crossentropy(net,t(tr.trainInd),y(tr.trainInd),{1},'regularization',net.performParam.regularization,'normalization',net.performParam.normalization)

and not

trp = mse(net,trainTargets,y)

Refer to the following resources: net.performFcn, crossentropy, Train Neural Network Using mse Performance Function, Analyze Shallow Neural Network Performance After Training, training record & help(net.performFcn) in command window

Best Answer

Related Solutions

MATLAB: MAPE for out-of-sample in neural network

MATLAB: Test, train and validation performance are so different from global performance in the neural network

Related Question