首页|Findings on Machine Learning Discussed by Investigators at University of Bonn (G amma-convergence of a Nonlocal Perimeter Arising In Adversarial Machine Learning )
Findings on Machine Learning Discussed by Investigators at University of Bonn (G amma-convergence of a Nonlocal Perimeter Arising In Adversarial Machine Learning )
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 News Daily News – Fresh data on Machine Learning are pre sented in a new report. According to news reporting out of Bonn, Germany, by New sRx editors, research stated, “In this paper we prove Gammaconvergence of a non local perimeter of Minkowski type to a local anisotropic perimeter. The nonlocal model describes the regularizing effect of adversarial training in binary class ifications.” Financial supporters for this research include German Research Foundation (DFG), German Research Foundation (DFG), Swedish Research Council. Our news journalists obtained a quote from the research from the University of B onn, “The energy essentially depends on the interaction between two distribution s modelling likelihoods for the associated classes. We overcome typical strict r egularity assumptions for the distributions by only assuming that they have boun ded BV densities. In the natural topology coming from compactness, we prove Gamm a-convergence to a weighted perimeter with weight determined by an anisotropic f unction of the two densities. Despite being local, this sharp interface limit re flects classification stability with respect to adversarial perturbations.”
BonnGermanyEuropeCyborgsEmerging TechnologiesMachine LearningUniversity of Bonn
NETL
NSTL
