Timezone: »

 
Poster
Towards Conceptual Compression
Karol Gregor · Frederic Besse · Danilo Jimenez Rezende · Ivo Danihelka · Daan Wierstra

Tue Dec 06 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #77
in Tuesday Posters »

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.

Keywords: Deep Learning or Neural Networks
[ PDF] 

Author Information

Karol Gregor (Google DeepMind)
Frederic Besse (Google DeepMind)
Danilo Jimenez Rezende (Google DeepMind)
Ivo Danihelka (DeepMind)
Daan Wierstra (Google DeepMind)

More from the Same Authors