Gradual Training Method for Denoising Auto Encoders
Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a deep network. We investigate a training scheme of a deep DAE, where DAE layers are gradually added and keep adapting as additional layers are...
Saved in:
| Published in | arXiv.org |
|---|---|
| Main Authors | , |
| Format | Paper |
| Language | English |
| Published |
Ithaca
Cornell University Library, arXiv.org
11.04.2015
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a deep network. We investigate a training scheme of a deep DAE, where DAE layers are gradually added and keep adapting as additional layers are added. We show that in the regime of mid-sized datasets, this gradual training provides a small but consistent improvement over stacked training in both reconstruction quality and classification error over stacked training on MNIST and CIFAR datasets. |
|---|---|
| AbstractList | Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a deep network. We investigate a training scheme of a deep DAE, where DAE layers are gradually added and keep adapting as additional layers are added. We show that in the regime of mid-sized datasets, this gradual training provides a small but consistent improvement over stacked training in both reconstruction quality and classification error over stacked training on MNIST and CIFAR datasets. |
| Author | Kalmanovich, Alexander Chechik, Gal |
| Author_xml | – sequence: 1 givenname: Alexander surname: Kalmanovich fullname: Kalmanovich, Alexander – sequence: 2 givenname: Gal surname: Chechik fullname: Chechik, Gal |
| BookMark | eNqNiksKwjAUAIMoWLV3CLgu5Kt1KVp14677EkyqKeU9zef-KngAVwMzsyBTQHATUggpeVUrIeakjHFgjInNVmgtCyLPwdhsRtoG48HDnV5deqClPQZ6dIA-fuU-J6QN3NC6EFdk1psxuvLHJVmfmvZwqZ4BX9nF1A2YA3xSJ1jNudJ8p-R_1xsgbzWM |
| ContentType | Paper |
| Copyright | 2015. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: 2015. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
| DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Engineering Collection ProQuest Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
| DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
| DatabaseTitleList | Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Physics |
| EISSN | 2331-8422 |
| Genre | Working Paper/Pre-Print |
| GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
| ID | FETCH-proquest_journals_20811451943 |
| IEDL.DBID | BENPR |
| IngestDate | Thu Oct 10 17:08:31 EDT 2024 |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-proquest_journals_20811451943 |
| OpenAccessLink | https://www.proquest.com/docview/2081145194?pq-origsite=%requestingapplication% |
| PQID | 2081145194 |
| PQPubID | 2050157 |
| ParticipantIDs | proquest_journals_2081145194 |
| PublicationCentury | 2000 |
| PublicationDate | 20150411 |
| PublicationDateYYYYMMDD | 2015-04-11 |
| PublicationDate_xml | – month: 04 year: 2015 text: 20150411 day: 11 |
| PublicationDecade | 2010 |
| PublicationPlace | Ithaca |
| PublicationPlace_xml | – name: Ithaca |
| PublicationTitle | arXiv.org |
| PublicationYear | 2015 |
| Publisher | Cornell University Library, arXiv.org |
| Publisher_xml | – name: Cornell University Library, arXiv.org |
| SSID | ssj0002672553 |
| Score | 2.9780107 |
| SecondaryResourceType | preprint |
| Snippet | Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a... |
| SourceID | proquest |
| SourceType | Aggregation Database |
| SubjectTerms | Coders Datasets Noise reduction Training |
| Title | Gradual Training Method for Denoising Auto Encoders |
| URI | https://www.proquest.com/docview/2081145194 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1bS8MwFD64FsE3r-icI6CvgaZNu-5JvLQbQseQCXsbaS7gSzvb7tXf7knJ9EHYYwgkIQnnfN-58AE8iIkxDGEsVVwKyoXhtETkTCObMhMJPnRqu5GLRTL_4G_reO0Cbq0rq9zbxN5Qq1raGDmS9JRZVdkpf9x-UasaZbOrTkJjAH6ITCHwwH_OFsv33yhLmEwQM0f_DG3vPfJT8Jdiq5szONLVORz3RZeyvYBo1gjbCkVWTqeBFL2eM0EgSV51VX9aIk-edl1Nsso2nzftJdzn2eplTvc7bdxvaDd_Z4-uwENar6-BBEwEHOGACnXAZZJMy9hwoYSRiqdG8hsYHVppeHj6Fk7Qtcc278HYCLyu2ek7dJ9dOYZBms_G7qZwVHxnP4credM |
| link.rule.ids | 783,787,12777,21400,33385,33756,43612,43817 |
| linkProvider | ProQuest |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1NS8NAEB20RfTmJ35UXdDrQtJM0vQkok2jNsVDhN7CZrMLXpo2Sf-_MyHVg9Dzwu6yu8x7M7OPB_CoRta6RGNlgVpJVBZlTsxZetwyUwFddMhq5GQexF_4vvAXXcGt7r5VbmNiG6iLUnONnJL00GVX2TE-rdaSXaO4u9pZaOxDHz3CalaKR9PfGsswGBFj9v6F2RY7omPof6qVqU5gzyxP4aD9cqnrM_CmlWIhlEg7lwaRtG7OgmikeDXL8pvTePG8aUoxWbL0vKrP4SGapC-x3K6UdW-hzv527l1Aj5J6cwnCcZWDRAaKoXFQB8E49y2qQlldYGg1XsFg10zXu4fv4TBOk1k2e5t_3MARgbzPHRDXHUCvqTbmloC0ye_a0_oBlTx5Rw |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Gradual+Training+Method+for+Denoising+Auto+Encoders&rft.jtitle=arXiv.org&rft.au=Kalmanovich%2C+Alexander&rft.au=Chechik%2C+Gal&rft.date=2015-04-11&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |