Deep Learning for One-Class Classification

I have Big Data that is textual in nature, and I have found some useful ressources for one-class classification using SVM and other models.

What I’m struggling to find is how to train a model using Deep Learning for one-class classification, and not ‘binary or multi-class classification for imbalanced datasets’, my data has only one class, and the model i want to create is not for anomaly detection or novelty detection.

My questions are:

1- Is is possible to create a deep learning one-class classification model, and if yes how?

2- if yes, How to evaluate such a model?

Thank You.