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

An effective deep learning development process is critical for widespreadindustrial adoption, particularly in the automotive sector. A typicalindustrial deep learning development cycle involves customizing andre-designing an off-the-shelf network architecture to meet the operationalrequirements of the target application, leading to considerable trial and errorwork by a machine learning practitioner. This approach greatly impedesdevelopment with a long turnaround time and the unsatisfactory quality of thecreated models. As a result, a development platform that can aid engineers ingreatly accelerating the design and production of compact, optimized deepneural networks is highly desirable. In this joint industrial case study, westudy the efficacy of the GenSynth AI-assisted AI design platform foraccelerating the design of custom, optimized deep neural networks forautonomous driving through human-machine collaborative design. We perform aquantitative examination by evaluating 10 different compact deep neuralnetworks produced by GenSynth for the purpose of object detection via aNASNet-based user network prototype design, targeted at a low-cost GPU-basedaccelerated embedded system. Furthermore, we quantitatively assess the talenthours and GPU processing hours used by the GenSynth process and three otherapproaches based on the typical industrial development process. In addition, wequantify the annual cloud cost savings for comprehensive testing using networksproduced by GenSynth. Finally, we assess the usability and merits of theGenSynth process through user feedback. The findings of this case study showedthat GenSynth is easy to use and can be effective at accelerating the designand production of compact, customized deep neural network.

Human-Machine Collaborative Design for Accelerated Design of Compact Deep Neural Networks for Autonomous Driving