Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representations

Steenbrugge, Xander, Leroux, Sam, Verbelen, Tim, Dhoedt, Bart

arXiv.org Machine Learning 

In this work we explore the generalization characteristics of unsupervised representation learning by leveraging disentangled VAE's to learn a useful latent space on a set of relational reasoning problems derived from Raven Progressive Matrices. We show that the latent representations, learned by unsupervised training using the right objective function, significantly outperform the same architectures trained with purely supervised learning, especially when it comes to generalization.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found