首页|Data on Machine Learning Discussed by Researchers at Johns Hopkins University (Dimensionless Machine Learning: Imposing Exact Units Equivariance)
Data on Machine Learning Discussed by Researchers at Johns Hopkins University (Dimensionless Machine Learning: Imposing Exact Units Equivariance)
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 – A new study on Machine Learning is now available. According to news reporting outof Baltimore, Maryland, by NewsRx editors, research stated, “Units equivariance (or units covariance) isthe exact symmetry that follows from the requirement that relationships among measured quantities ofphysics relevance must obey self-consistent dimensional scalings. Here, we express this symmetry in termsof a (noncompact) group action, and we employ dimensional analysis and ideas from equivariant machinelearning to provide a methodology for exactly units-equivariant machine learning: For any given learningtask, we first construct a dimensionless version of its inputs using classic results from dimensional analysisand then perform inference in the dimensionless space.”
BaltimoreMarylandUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMachine LearningJohns Hopkins University
NETL
NSTL
