- 1、本文档共8页,可阅读全部内容。
- 2、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
Deep Learning via Semi-Supervised Embedding
Jason Weston∗ jasonw@
Fr´ed´eric Ratle† frederic.ratle@
Ronan Collobert∗ collober@
(∗) NEC Labs America, 4 Independence Way, Princeton, NJ 08540 USA
(†) IGAR, University of Lausanne, Amphipˆole, 1015 Lausanne, Switzerland
Abstract tance measure based on a nonlinear manifold embed-
We show how nonlinear embedding algo- ding as a first step (Chapelle et al., 2003; Chapelle
rithms popular for use with shallow semi- Zien, 2005). Transductive Support Vector Machines
supervised learning techniques such as ker- (TSVMs) (Vapnik, 1998) (which employs a kind of
nel methods can be applied to deep multi- clustering) and LapSVM (Belkin et al., 2006) (which
layer architectures, either as a regularizer at employs a kind of embedding) are examples of meth-
the output layer, or on each layer of the ar- ods that are joint in their use of unlabeled data and
chitecture. This provides a simple alterna- labeled data, but their architecture is still shallow.
tive to existing approaches to deep learning Deep architectures seem a natural choice in hard AI
whilst yielding competitive error rates com- tasks which involve several sub-tasks which can be
pared to those methods, and existing shallow coded into the layers of the architecture. As argued by
semi-supervised techniques.
您可能关注的文档
- 《GE_PLC90-70指令培训》.pdf
- 《GE的6+sigma》.ppt
- 《GE自白—我们如何培养经理人》.doc
- 《GHS_MSDS_丁二烯_中文》.pdf
- 《GL 总账管理ORACLE ERP培训.PPT》.pdf
- 《Global dynamics of the generalized Lorenz systems having invariant》.pdf
- 《GNSS(GPS+GLONASS)卫星导航开发验证平台-宣传手册》.pdf
- 《Gout_Part_1_ACR-12-0014》.pdf
- 《GPPRO-CNT-MS03JE-CPa_eng》.pdf
- 《GPS与北斗卫星导航系统》.doc
文档评论(0)