GenSynth: a generative synthesis approach to learning generative machines for generate efficient neural networks

GenSynth: a generative synthesis approach to learning generative machines for generate efficient neural networks

The tremendous potential exhibited by deep learning is often offset by architectural and computational complexity, making widespread deployment a challenge for edge scenarios such as mobile and other consumer devices. To tackle this challenge, we explore the following idea: Can we learn generative m...

Full description

Bibliographic Details
Main Authors: Alexander Wong, Mohammad Javad Shafiee, Brendan Chwyl, Francis Li
Format: Article
Language:English
Published: Wiley 2019-09-01
Series:Electronics Letters
Subjects:
computational complexity
generative machines
efficient network architectures
GenSynth
generator‐inquisitor pair
unique highly efficient deep neural networks
Online Access:https://doi.org/10.1049/el.2019.1719

Internet

https://doi.org/10.1049/el.2019.1719

Similar Items