Robotics & Machine Learning Daily News2024,Issue(Jan.25) :64-65.

Reports from University of Maryland Baltimore County Advance Knowledge in Networks (Reg-tunev2: a Hardware-aware and Multiobjective Regression-based Fine-tuning Approach for Deep Neural Networks On Embedded Platforms)

Robotics & Machine Learning Daily News2024,Issue(Jan.25) :64-65.

Reports from University of Maryland Baltimore County Advance Knowledge in Networks (Reg-tunev2: a Hardware-aware and Multiobjective Regression-based Fine-tuning Approach for Deep Neural Networks On Embedded Platforms)

扫码查看

Abstract

By a News Reporter-Staff News Editor at Network Daily News - Research findingson Networks are discussed in a new report. According to news reporting originating in Baltimore, Maryland,by NewsRx journalists, research stated, “Fine-tuning deep neural networks (DNNs) for deployment hastraditionally relied on computationally intensive methods such as grid searches and neural architecturesearches, which may not consider hardware-aware metrics. Moreover, it is essential to consider multipleobjectives to develop a range of solutions for tiny machine learning hardware deployment with real-timelatency and low power constraints.”

Key words

Baltimore/Maryland/United States/North and Central America/Networks/Neural Networks/University of Maryland Baltimore County

引用本文复制引用

出版年

2024
Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
浏览量1
段落导航相关论文