首页|New Machine Learning Study Findings Have Been Reported by Investigators at Imperial College (Learning Closure Relations Using Differentiable Programming: an Example In Radiation Transport)
New Machine Learning Study Findings Have Been Reported by Investigators at Imperial College (Learning Closure Relations Using Differentiable Programming: an Example In Radiation Transport)
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 DailyNews Daily News - Investigators publish new report on Ma chine Learning. According to news reportingout of London, United Kingdom, by Ne wsRx editors, research stated, “Reduced order models with aprioriunknown closu re relations are ubiquitous in transport problems. In this work, we present a machine-learning approach to finding closure relations utilising differentiable pr ogramming.”Funders for this research include Eric and Wendy Schmidt AI in Science Postdocto ral Fellowship,Schmidt Futures program.Our news journalists obtained a quote from the research from Imperial College, “ We use the Su Olsonradiation transport test problem as an example training data set. We present novel closures for secondangular moment (variable Eddington fa ctor), third angular moment and flux-limited diffusion models.We evaluate the i mprovement of the machine-learnt closures over those from the literature. Theseimprovements are then tested by considering a modification to the Su Olson probl em.”
LondonUnited KingdomEuropeCyborgsEmerging TechnologiesMachine LearningImperial College