DLphi 的神谕
机器学习
2019-01-29 v2 机器学习
摘要
我们提出一种基于深度学习与集合论的新颖技术，其产生了卓越的分类与预测结果。在能获取足量带标签训练数据的情况下，即便训练数据与测试数据完全无关，我们的方法也几乎总能预测测试数据的标签。换言之，我们在特定设定下证明：只要能获取足够多的数据点，数据的质量无关紧要。
引用
@article{arxiv.1901.05744,
title = {The Oracle of DLphi},
author = {Dominik Alfke and Weston Baines and Jan Blechschmidt and Mauricio J. del Razo Sarmina and Amnon Drory and Dennis Elbrächter and Nando Farchmin and Matteo Gambara and Silke Glas and Philipp Grohs and Peter Hinz and Danijel Kivaranovic and Christian Kümmerle and Gitta Kutyniok and Sebastian Lunz and Jan Macdonald and Ryan Malthaner and Gregory Naisat and Ariel Neufeld and Philipp Christian Petersen and Rafael Reisenhofer and Jun-Da Sheng and Laura Thesing and Philipp Trunschke and Johannes von Lindheim and David Weber and Melanie Weber},
journal= {arXiv preprint arXiv:1901.05744},
year = {2019}
}