Non traceable loss function in neural network

Question

Pere Garau Burguera 2020-9-25

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/599608-non-traceable-loss-function-in-neural-network

回答： Divya Gaddipati 2020-10-15

采纳的回答： Divya Gaddipati

在 MATLAB Online 中打开

Hi,

I would want to know if there's any possibility of having a loss function that looks like this:

This is used in a siamese network for metric learning. There are 2 identical networks with the same weights, where the Xs are the inputs and Y are the outputs. The thing is that the operations performed on the dlarrays are not permitted so the gradients cannot be computed.

Is there an alternative way to make this work?

function loss = lossfunc(Y1,Y2,X1,X2,dist)
    % accepts the network's predictions Y1, Y2, the inputs
    % X1, X2, and the true distance between X1 and X2, and returns the loss value.
    
     loss = .5*((X1-X2)'*pinv(Y1*Y1')*(X1-X2)...
             + (X1-X2)'*pinv(Y2*Y2')*(X1-X2))...
               -dist^2);
end