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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Over the last five years Deep Neural Nets have offered more accuratesolutions to many problems in speech recognition, and computer vision, andthese solutions have surpassed a threshold of acceptability for manyapplications. As a result, Deep Neural Networks have supplanted otherapproaches to solving problems in these areas, and enabled many newapplications. While the design of Deep Neural Nets is still something of an artform, in our work we have found basic principles of design space explorationused to develop embedded microprocessor architectures to be highly applicableto the design of Deep Neural Net architectures. In particular, we have usedthese design principles to create a novel Deep Neural Net called SqueezeNetthat requires as little as 480KB of storage for its model parameters. We havefurther integrated all these experiences to develop something of a playbook forcreating small Deep Neural Nets for embedded systems.

Keynote: Small Neural Nets Are Beautiful: Enabling Embedded Systems with Small Deep-Neural-Network Architectures