A1:笑得海潮 B3:冒泡的崔 D2:Cornell University,Computer Vision Group H2:冰河的博客 G3:丕子博客 K1:MLA CHINA K4:斯坦福视觉实验室 L4:MIT 机器学习实验室
现在的位置: 首页科研>正文
cat_ico37 category
LETOR 4.0 数据集今年刚刚发布
发表于845 天前 科研 暂无评论 ⁄ 被围观 636 次+

特点:数据量大了,数据细致准确。针对性强,包括监督学习、半监督学习、排序聚集、类回归学习等等。并且开放了比较新的一些rank算法的源码以及接口,而且有数据可以和自己的实验进行对比了。哈哈,好!

  • Two large scale query sets were used, with thousands of queries;
  • Datasets for four kinds of ranking settings were provided: supervised ranking, semi-supervised ranking, rank aggregation, and listwise ranking;
  • Low level features were included for investigation;
  • Several baselines were included.
  • http://research.microsoft.com/en-us/um/beijing/projects/letor/

    给我留言


    / 快捷键:Ctrl+Enter

    无觅相关文章插件,快速提升流量

    不想听你唠叨×