Misclassification cost in neural networks
조회 수: 3 (최근 30일)
이전 댓글 표시
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?
댓글 수: 1
답변 (0개)
참고 항목
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!