However, most existing autoencoder-based methods discard the reconstruction of auxiliary information, which poses a huge challenge for better representation learning and model scalability.

In this white paper, Bloomberg researchers show the applicability of deep latent variable models (DLVMs) in ESG datasets, outperforming classical imputation models as well as classical predictive ...

The autoencoder network model for HIV classification, proposed in this paper, thus outperforms the conventional feedforward neural network models and is a much better classifier.