A Novel Variational Autoencoder with Applications to Generative Modelling, Classification, and Ordinal Regression [article]

Joel Jaskari, Jyri J. Kivinen
2018 arXiv   pre-print
We develop a novel probabilistic generative model based on the variational autoencoder approach. Notable aspects of our architecture are: a novel way of specifying the latent variables prior, and the introduction of an ordinality enforcing unit. We describe how to do supervised, unsupervised and semi-supervised learning, and nominal and ordinal classification, with the model. We analyze generative properties of the approach, and the classification effectiveness under nominal and ordinal
more » ... cation, using two benchmark datasets. Our results show that our model can achieve comparable results with relevant baselines in both of the classification tasks.
arXiv:1812.07352v2 fatcat:yvk5gcnlyzadfl23sgmjxgmx2q