- 博客(1)
- 资源 (1)
- 收藏
- 关注
转载 下载积分攻略
下载积分攻略:1. 个人设置里进行手机绑定CSDN账户 奖励50分 (右上角设置-账户安全-手机绑定)2. 完成任务送若干分积分 http://task.csdn.net/3. 上传有效资源获取积分(上传非法,广告资源用户,将被扣除一定积分,严重者封号)。 · 上传自己设分资源被下载,下载量×资源分,100分封顶。 · 上传0分资源被下载,下载量×系统奖励1分,100封顶4. ...
2018-07-03 15:17:08 139 1
aaai18eForest
Auto-encoding is an important task which is typically re-
alized by deep neural networks (DNNs) such as convolu-
tional neural networks (CNN). In this paper, we propose En-
coderForest (abbrv. eForest), the first tree ensemble based
auto-encoder. We present a procedure for enabling forests
to do backward reconstruction by utilizing the Maximal-
Compatible Rule (MCR) defined by the decision paths of
the trees, and demonstrate its usage in both supervised and
unsupervised setting. Experiments show that, compared with
DNN based auto-encoders, eForest is able to obtain lower re-
construction error with fast training speed, while the model
itself is reusable and damage-tolerable
2018-07-03
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人