The Oracle of DLphi
Machine Learning
2019-01-29 v2 Machine Learning
Abstract
We present a novel technique based on deep learning and set theory which yields exceptional classification and prediction results. Having access to a sufficiently large amount of labelled training data, our methodology is capable of predicting the labels of the test data almost always even if the training data is entirely unrelated to the test data. In other words, we prove in a specific setting that as long as one has access to enough data points, the quality of the data is irrelevant.
Keywords
Cite
@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}
}