A company is developing a new image classification model that categorizes photos into three classes: 'Animals', 'Nature', and 'Urban'. They noticed that their model struggles to correctly classify images of animals in urban settings. Which multi-class loss function would best help them optimize their model's performance in this scenario?

Logistic loss, also called cross‑entropy, turns the model’s raw scores into probabilities for each class. Other options are incorrect because The hinge loss is made for binary decisions and pushes predictions to be far from the decision boundary; The Neyman-Pearson loss focuses on controlling one type of error, like false positives.