File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.neucom.2015.02.023
- Scopus: eid_2-s2.0-84927959031
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Article: Laplacian Auto-Encoders: An explicit learning of nonlinear data manifold
Title | Laplacian Auto-Encoders: An explicit learning of nonlinear data manifold |
---|---|
Authors | |
Keywords | Auto-encoders Deep learning Image classification Manifold learning |
Issue Date | 2015 |
Citation | Neurocomputing, 2015, v. 160, p. 250-260 How to Cite? |
Abstract | A key factor contributing to the success of many auto-encoders based deep learning techniques is the implicit consideration of the underlying data manifold in their training criteria. In this paper, we aim to make this consideration more explicit by training auto-encoders completely from the manifold learning perspective. We propose a novel unsupervised manifold learning method termed Laplacian Auto-Encoders (LAEs). Starting from a general regularized function learning framework, LAE regularizes training of auto-encoders so that the learned encoding function has the locality-preserving property for data points on the manifold. By exploiting the analog relation between the graph Laplacian and the Laplace-Beltrami operator on the continuous manifold, we derive discrete approximations of the first- and higher-order auto-encoder regularizers that can be applied in practical scenarios, where only data points sampled from the distribution on the manifold are available. Our proposed LAE has potentially better generalization capability, due to its explicit respect of the underlying data manifold. Extensive experiments on benchmark visual classification datasets show that LAE consistently outperforms alternative auto-encoders recently proposed in deep learning literature, especially when training samples are relatively scarce. |
Persistent Identifier | http://hdl.handle.net/10722/345072 |
ISSN | 2023 Impact Factor: 5.5 2023 SCImago Journal Rankings: 1.815 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jia, Kui | - |
dc.contributor.author | Sun, Lin | - |
dc.contributor.author | Gao, Shenghua | - |
dc.contributor.author | Song, Zhan | - |
dc.contributor.author | Shi, Bertram E. | - |
dc.date.accessioned | 2024-08-15T09:25:03Z | - |
dc.date.available | 2024-08-15T09:25:03Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | Neurocomputing, 2015, v. 160, p. 250-260 | - |
dc.identifier.issn | 0925-2312 | - |
dc.identifier.uri | http://hdl.handle.net/10722/345072 | - |
dc.description.abstract | A key factor contributing to the success of many auto-encoders based deep learning techniques is the implicit consideration of the underlying data manifold in their training criteria. In this paper, we aim to make this consideration more explicit by training auto-encoders completely from the manifold learning perspective. We propose a novel unsupervised manifold learning method termed Laplacian Auto-Encoders (LAEs). Starting from a general regularized function learning framework, LAE regularizes training of auto-encoders so that the learned encoding function has the locality-preserving property for data points on the manifold. By exploiting the analog relation between the graph Laplacian and the Laplace-Beltrami operator on the continuous manifold, we derive discrete approximations of the first- and higher-order auto-encoder regularizers that can be applied in practical scenarios, where only data points sampled from the distribution on the manifold are available. Our proposed LAE has potentially better generalization capability, due to its explicit respect of the underlying data manifold. Extensive experiments on benchmark visual classification datasets show that LAE consistently outperforms alternative auto-encoders recently proposed in deep learning literature, especially when training samples are relatively scarce. | - |
dc.language | eng | - |
dc.relation.ispartof | Neurocomputing | - |
dc.subject | Auto-encoders | - |
dc.subject | Deep learning | - |
dc.subject | Image classification | - |
dc.subject | Manifold learning | - |
dc.title | Laplacian Auto-Encoders: An explicit learning of nonlinear data manifold | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.neucom.2015.02.023 | - |
dc.identifier.scopus | eid_2-s2.0-84927959031 | - |
dc.identifier.volume | 160 | - |
dc.identifier.spage | 250 | - |
dc.identifier.epage | 260 | - |
dc.identifier.eissn | 1872-8286 | - |