https://datasciencepreparation.com/blog/articles/what-is-the-0-1-loss-function-why-cant-the-0-1-loss-function-or-classification-error-be-used-as-a-loss-function-for-optimizing-a-deep-neural-network/
Prepare for Data Science Interviews - Check out! What is the 0-1 loss function? Why can't the 0-1 loss function or classification error be used as a loss function for optimizing a deep neural network?