Skip to yearly menu bar Skip to main content


Towards Conceptual Compression

Karol Gregor · Frederic Besse · Danilo Jimenez Rezende · Ivo Danihelka · Daan Wierstra

Area 5+6+7+8 #77

Keywords: [ Deep Learning or Neural Networks ]


We introduce convolutional DRAW, a homogeneous deep generative model achieving state-of-the-art performance in latent variable image modeling. The algorithm naturally stratifies information into higher and lower level details, creating abstract features and as such addressing one of the fundamentally desired properties of representation learning. Furthermore, the hierarchical ordering of its latents creates the opportunity to selectively store global information about an image, yielding a high quality 'conceptual compression' framework.

Live content is unavailable. Log in and register to view live content