期刊
FRONTIERS IN GENETICS
卷 12, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fgene.2021.655287
关键词
training optimization; machine learning; genomic selection; genomic prediction; image classification; multi-objective optimization; mixed models
资金
- Department of Agriculture, Food and the Marine grant [2017EN104]
- European Union's Horizon 2020 research and innovation program [818144]
- Severo Ochoa Program for Centres of Excellence in RD
- Beatriz Galindo Program from the Ministerio de Educacion y Formacion Professional of Spain [BEAGAL18/00115]
- Severo Ochoa Program for Centres of Excellence in R&D from the Agencia Estatal de Investigacion of Spain [SEV-2016-0672]
- H2020 Societal Challenges Programme [818144] Funding Source: H2020 Societal Challenges Programme
This paper introduces an R package, TrainSel, for selecting training populations to address the main barrier of supervised learning in emerging applications. By carefully selecting training examples, the accuracy of predictive models can be improved.
A major barrier to the wider use of supervised learning in emerging applications, such as genomic selection, is the lack of sufficient and representative labeled data to train prediction models. The amount and quality of labeled training data in many applications is usually limited and therefore careful selection of the training examples to be labeled can be useful for improving the accuracies in predictive learning tasks. In this paper, we present an R package, TrainSel, which provides flexible, efficient, and easy-to-use tools that can be used for the selection of training populations (STP). We illustrate its use, performance, and potentials in four different supervised learning applications within and outside of the plant breeding area.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据