← Back to papers
2016 NIPS NeurIPS 2016

Towards Conceptual Compression

Abstract

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.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning
🧭 Keyword Pioneer — hierarchical latent
🐣 Hot Topic Early Bird — latent variable model
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

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

Topics

Machine Learning > Core Methods > Representation Learning Deep Learning > Architectures > Neural Networks Deep Learning > Models > Generative Models Deep Learning > Learning Types > Representation Learning

Keywords

representation learning latent variable model convolutional neural network deep generative model hierarchical latent conceptual compression
Download PDF

Related papers

Bayesian Intermittent Demand Forecasting for Large Inventories 2016
Dynamic Network Surgery for Efficient DNNs 2016
Beyond Exchangeability: The Chinese Voting Process 2016
Safe and Efficient Off-Policy Reinforcement Learning 2016
Tagger: Deep Unsupervised Perceptual Grouping 2016