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

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.

[Greg Heath]

Can t be 0?

Greg

[Kamuran Turksoy]

Not in my application.

Answer 1

[Kamuran Turksoy]

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.

[Jinlong Fu]

In my view, it should be as follows:

net.performFcn='mse'; % mean suqare error

net= train(net,x,t,{},{},1./t.^2); % 1./t.^2 is the error weight

or

net.performFcn='mae'; % mean absolut error

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

Answer 2

[Greg Heath]

You have at least 2 obstacles:

 1. When t --> 0

 2. abs is not differentiable

 If t --> 0 is not a problem try 

 myperf = mse( 1-y./t);

Hope this helps.

Thank you for formally accepting my answer

Greg

[Kamuran Turksoy]

In my application t cannot be 0.

I could use myperf = mse(1-y./t) or myperf = mse((t-y)./t).

The question is how to use myperf during the model training?