基于新发展理念背景下综合评价安徽省农业农村高质量发展水平,对推动安徽省农业农村高质量发展具有重要意义。以安徽省2010~2020年的农业农村相关数据作为研究对象,采用熵权法研究了近年来安徽省农业农村高质量发展情况。结果表明:2010~2020年安徽省农业农村高质量发展水平逐步提高;从指标权重上看,绿色和协调指数所占权重较大。最后,从创新、协调、绿色、开放、共享五个方面提出对策和建议,对提升安徽省农业农村高质量发展提供参考依据。The comprehensive evaluation of the high-quality development level of agriculture and rural areas in Anhui Province based on the new development concept is of great significance for promoting the high-quality development of agriculture and rural areas in Anhui Province. Taking the agricultural and rural related data of Anhui Province from 2010 to 2020 as the research object, the entropy weight method was used to study the high-quality development of agriculture and rural areas in Anhui Province in recent years. The results indicate that the level of high-quality development of agriculture and rural areas in Anhui Province has gradually improved from 2010 to 2020;from the perspective of indicator weights, the green and coordination indices have a higher weight. Finally, countermeasures and suggestions are proposed from five aspects: innovation, coordination, green, openness, and sharing, providing reference for improving the high-quality development of agriculture and rural areas in Anhui Province.
当标注样本匮乏时,半监督学习利用大量未标注样本解决标注瓶颈的问题,但由于未标注样本和标注样本来自不同领域,可能造成未标注样本存在质量问题,使得模型的泛化能力变差,导致分类精度下降.为此,基于wordMixup方法,提出针对未标注样本进行数据增强的u-wordMixup方法,结合一致性训练框架和Mean Teacher模型,提出一种基于u-wordMixup的半监督深度学习模型(semi-supervised deep learning model based on u-wordMixup,SD-uwM).该模型利用u-wordMixup方法对未标注样本进行数据增强,在有监督交叉熵和无监督一致性损失的约束下,能够提高未标注样本质量,减少过度拟合.在AGNews、THUCNews和20 Newsgroups数据集上的对比实验结果表明,所提出方法能够提高模型的泛化能力,同时有效提高时间性能.
当目标领域缺少足够多的标注数据时,迁移学习利用相关源领域的标注数据,辅助提升目标域的学习性能,但是目标域与源域的数据通常不满足独立同分布,容易导致“负迁移”问题.本文在有监督主题模型(Supervised LDA,SLDA)的基础上,融合迁移学习方法提出一种共享主题知识的迁移主题模型(Transfer SLDA,Tr-SLDA),提出Tr-SLDA-Gibbs主题采样新方法,在类别标签的约束下对不同领域文档中的词采取不同的采样策略,且无需指定主题个数.辅助源域与目标域共享潜在主题空间,Tr-SLDA通过发现潜在共享主题与不同领域类别之间的语义关联从源域迁移知识,可以有效解决“负迁移”问题.基于Tr-SLDA迁移主题模型提出Tr-SLDA-TC(Tr-SLDA Text Categorization)文本分类方法.对比实验表明,该方法可有效利用源域知识来提高目标领域的分类性能.
暂无评论