English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep generative models provide a powerful set of tools to understandreal-world data. But as these models improve, they increase in size andcomplexity, so their computational cost in memory and execution time grows.Using binary weights in neural networks is one method which has shown promisein reducing this cost. However, whether binary neural networks can be used ingenerative models is an open problem. In this work we show, for the first time,that we can successfully train generative models which utilize binary neuralnetworks. This reduces the computational cost of the models massively. Wedevelop a new class of binary weight normalization, and provide insights forarchitecture designs of these binarized generative models. We demonstrate thattwo state-of-the-art deep generative models, the ResNet VAE and Flow++ models,can be binarized effectively using these techniques. We train binary modelsthat achieve loss values close to those of the regular models but are 90%-94%smaller in size, and also allow significant speed-ups in execution time.

Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks