LGJul 16, 2017
Minimax deviation strategies for machine learning and recognition with short learning samples
arXiv:1707.04849v11 citations
Originality Incremental advance
AI Analysis
This tackles the issue of limited training data for machine learning practitioners, but appears incremental as it builds on existing minimax approaches.
The paper addresses the problem of small learning samples in machine learning by introducing minimax deviation learning, which overcomes flaws in maximum likelihood and minimax learning, though no concrete numerical results are provided.
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.