I have a deep-learning model, where you can predict 5 different class (0-4). I want a model that punishes predictions that are more wrong. So if the model predicts 3 and it is a 4, it's not as bad as if it predicts a 0 and it is a 4 actually. Which loss function should I use?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.