Misclassification cost in neural networks

I was wondeing if it is possible to put weights on false positive and false negatives, the same as the misclassification cost array in random forest and SVM?

Explaining what I mean by misclassification cost: Misclassification cost, specified as a numeric square matrix, where Cost(i,j) is the cost of classifying a point into class j if its true class is i. For two-class learning, if you specify the cost matrix ? (see Cost), then the software updates the class prior probabilities p (see Prior) to pc by incorporating the penalties described in ?. (at https://au.mathworks.com/help/stats/classificationsvm.html)

Defining C in a matrix like this (C=[0 alpha beta 0]) you will be able to put weights on FP and FN by varying beta and alpha. Is this also possible in neural nets?

[M J]

Hi, did you figure it out? I'm currently facing the same problem. Thanks!