首页|Findings from University of Oxford Update Understanding of Machine Learning (Pla nter: Rapid Prototyping of In-network Machine Learning Inference)
Findings from University of Oxford Update Understanding of Machine Learning (Pla nter: Rapid Prototyping of In-network Machine Learning Inference)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily NewsResearch findings on Machine Learning are discuss ed in a new report. According to news reporting out of Oxford, United Kingdom, b y NewsRx editors, research stated, "In-network machine learning inference provid es high throughput and low latency. It is ideally located within the network, po wer efficient, and improves applications' performance." Financial supporters for this research include VMware, European Union (EU), Inte l Corporation, Nvidia Corporation.Our news journalists obtained a quote from the research from the University of O xford, "Despite its advantages, the bar to in-network machine learning research is high, requiring significant expertise in programmable data planes, in additio n to knowledge of machine learning and the application area. Existing solutions are mostly one-time efforts, hard to reproduce, change, or port across platforms . In this paper, we present Planter: a modular and efficient open-source framewo rk for rapid prototyping of in-network machine learning models across a range of platforms and pipeline architectures. By identifying general mapping methodolog ies for machine learning algorithms, Planter introduces new machine learning map pings and improves existing ones. It provides users with several example use cas es and supports different datasets, and was already extended by users to new fie lds and applications. Our evaluation shows that Planter improves machine learnin g performance compared with previous model-tailored works, while significantly r educing resource consumption and co-existing with network functionality."
OxfordUnited KingdomEuropeCyborgsEmerging TechnologiesMachine LearningUniversity of Oxford
NETL
NSTL
