Hello Juan!

If you are using neural networks, which are the most common application for entropy as a loss function, you can use a variety of cross-entropy or KL divergence losses. Usually it doesn't make much sense to evaluate a model with entropy since it's more of a metric to help machines understand where they are, for a metric to evaluate the model on (and not to train it with) using something simple and interpretable like accuracy is best.

Hope this helps!

ML & CS enthusiast. Let’s connect: https://www.linkedin.com/in/andre-ye.

ML & CS enthusiast. Let’s connect: https://www.linkedin.com/in/andre-ye.