Using a cross-entropy loss function in the Deep Learning Toolbox for a probability distribution target

4 次查看（过去 30 天）

Andreas 2019-6-16

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/467318-using-a-cross-entropy-loss-function-in-the-deep-learning-toolbox-for-a-probability-distribution-targ

I am trying to predict a probability distribution with the deep learning toolbox. In other words, my annotations for each training example consists of a vector of probabilities, which sum to 1. The Deep Learning Toolbox in MATLAB puts a very restrictive condition on when the cross entropy function can be used, namely only for class labels. Is there any solution or do I need to migrate to another machine learning library and programming language?