09 2017 档案

摘要:update for every unique interaction, that is to choose a set of negative examples for every interaction in the train, repository name: lightfm radius 阅读全文
posted @ 2017-09-13 15:50 Fassy 阅读(162) 评论(0) 推荐(0)
摘要:User based center, and using the negative examples around the center: testsize: 1000 results: testsize:10000 results: 阅读全文
posted @ 2017-09-11 19:07 Fassy 阅读(214) 评论(0) 推荐(0)
摘要:To be continued... 阅读全文
posted @ 2017-09-07 16:22 Fassy 阅读(109) 评论(0) 推荐(0)
摘要:Taking almost a week break, I am back..... 阅读全文
posted @ 2017-09-07 16:21 Fassy 阅读(150) 评论(0) 推荐(0)
摘要:After testing with the data, the results we got were not what we expected. The test AUC is approximately 50 percent, which means that it is almost the 阅读全文
posted @ 2017-09-04 16:30 Fassy 阅读(120) 评论(0) 推荐(0)