Minimax deviation strategies for machine learning and recognition with short learning samples
Machine Learning
2017-07-18 v1
Abstract
The article is devoted to the problem of small learning samples in machine learning. The flaws of maximum likelihood learning and minimax learning are looked into and the concept of minimax deviation learning is introduced that is free of those flaws.
Keywords
Cite
@article{arxiv.1707.04849,
title = {Minimax deviation strategies for machine learning and recognition with short learning samples},
author = {Michail Schlesinger and Evgeniy Vodolazskiy},
journal= {arXiv preprint arXiv:1707.04849},
year = {2017}
}