Reconstruction of handwritten digit images using autoencoder neural networks
This paper compares the performances of three types of autoencoder neural networks, namely, the traditional autoencoder with restricted Boltzmann machine (RBM), the stacked autoencoder without RBM and the stacked autoencoder with RBM based on the efficiency for reconstruction of handwritten digit im...
Uložené v:
| Vydané v: | 2008 Canadian Conference on Electrical and Computer Engineering s. 000465 - 000470 |
|---|---|
| Hlavní autori: | , |
| Médium: | Konferenčný príspevok.. |
| Jazyk: | English |
| Vydavateľské údaje: |
IEEE
01.05.2008
|
| Predmet: | |
| ISBN: | 9781424416424, 1424416426 |
| ISSN: | 0840-7789 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | This paper compares the performances of three types of autoencoder neural networks, namely, the traditional autoencoder with restricted Boltzmann machine (RBM), the stacked autoencoder without RBM and the stacked autoencoder with RBM based on the efficiency for reconstruction of handwritten digit images. Experiments are performed to determine the reconstruction error in all the three cases using the same architecture configuration and training algorithm. The results show that the RBM stacked autoencoder gives better performance in terms of the reconstruction error compared to the other two architectures. We also show that all the architectures outperform PCA in terms of the reconstruction error. |
|---|---|
| AbstractList | This paper compares the performances of three types of autoencoder neural networks, namely, the traditional autoencoder with restricted Boltzmann machine (RBM), the stacked autoencoder without RBM and the stacked autoencoder with RBM based on the efficiency for reconstruction of handwritten digit images. Experiments are performed to determine the reconstruction error in all the three cases using the same architecture configuration and training algorithm. The results show that the RBM stacked autoencoder gives better performance in terms of the reconstruction error compared to the other two architectures. We also show that all the architectures outperform PCA in terms of the reconstruction error. |
| Author | Tan, C.C. Eswaran, C. |
| Author_xml | – sequence: 1 givenname: C.C. surname: Tan fullname: Tan, C.C. organization: Centre for Multimedia & Distrib. Comput., Multimedia Univ., Cyberjaya – sequence: 2 givenname: C. surname: Eswaran fullname: Eswaran, C. organization: Centre for Multimedia & Distrib. Comput., Multimedia Univ., Cyberjaya |
| BookMark | eNpVkM1KxDAUhSOO4Mw4L6CbvEDHmzZtkqWU-gMFQd0PmeamRsdEkpTBt7fgbFx9nM3hO2dFFj54JOSawZYxULdt27XdtgSQW143vBbijGyUkIyXnLOGV-z8Xy75gixBciiEkOqSrFL6AAAuG74k_QsOwaccpyG74Gmw9F17c4wuZ_TUuNFl6r70iIlOyfmR6ikH9EMwGKnHKerDjHwM8TNdkQurDwk3J67J63331j4W_fPDU3vXF05BLhA0MqE06rLkVqGyqlYV6nkc1APAIMt9jRoV7jUaxgbDLLPGNFqoRslqTW7-Wh0i7r7jbBd_dqcrql_leVRi |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/CCECE.2008.4564577 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library (IEL) (UW System Shared) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISBN | 9781424416431 1424416434 |
| EndPage | 000470 |
| ExternalDocumentID | 4564577 |
| Genre | orig-research |
| GroupedDBID | 29F 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR AAWTH ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP IPLJI M43 OCL RIE RIL RIO RNS |
| ID | FETCH-LOGICAL-i90t-e0ae179aea224f9e9f9593ea11005c00c82b5eae9ebaed11cd1f1fdd6a796983 |
| IEDL.DBID | RIE |
| ISBN | 9781424416424 1424416426 |
| ISSN | 0840-7789 |
| IngestDate | Wed Aug 27 02:14:57 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i90t-e0ae179aea224f9e9f9593ea11005c00c82b5eae9ebaed11cd1f1fdd6a796983 |
| PageCount | 6 |
| ParticipantIDs | ieee_primary_4564577 |
| PublicationCentury | 2000 |
| PublicationDate | 2008-May |
| PublicationDateYYYYMMDD | 2008-05-01 |
| PublicationDate_xml | – month: 05 year: 2008 text: 2008-May |
| PublicationDecade | 2000 |
| PublicationTitle | 2008 Canadian Conference on Electrical and Computer Engineering |
| PublicationTitleAbbrev | CCECE |
| PublicationYear | 2008 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0004864 ssj0000453620 |
| Score | 1.4271533 |
| Snippet | This paper compares the performances of three types of autoencoder neural networks, namely, the traditional autoencoder with restricted Boltzmann machine... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 000465 |
| SubjectTerms | Autoencoder Backpropagation Decoding dimensionality reduction Distributed computing Feedforward neural networks Image reconstruction Information technology Multi-layer neural network Multimedia computing neural network Neural networks Principal component analysis Restricted Boltzmann Machine |
| Title | Reconstruction of handwritten digit images using autoencoder neural networks |
| URI | https://ieeexplore.ieee.org/document/4564577 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ25T8MwFMattmKAhaNF3PLASKjdHLbnqBVDVVUCoW6Vj-cqEjSoTeHfx3bSFiQWphxLomfFz-_l-35G6F4baYWkKkq08d0qJiIlwUbKEAEpUSILeyy9jtlkwmczMW2hh50XBgCC-Awe_Wn4l29KvfGtsn5AnzDWRm3GstqrteunuKWJm4vJ3hPJa3QU94o5xsXW1OXKg0G2ZT0118nWTUNEP8-H-bDWWDaP-7XvSkg7o-P_vfAJ6u39e3i6y0ynqAXLM3T0Az3YRWNfd-7psbi02PfQv1ZF5VbR2BSLosLFu5tt1thr4xdYbqrSUy8NrLCnYMo3dwga8nUPPY-GL_lT1OysEBWCVBEQCe5DlCBdArcChPV4YpAeH5dqQjQfqBQkCHDjZijVhlpqjckkE5ng8TnqLMslXCDMUxYrFtvYJDKxnMospVorq1wVk2nKL1HXR2X-UaMz5k1Arv6-fY0OazmG1xPeoI6LAdyiA_1ZFevVXRjvb45Up0c |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ1JT8MwEIWtUpCAC0uL2PGBI6Fxs9g-R0VFhKoSFeqt8jKuIkGD2hT-PnaStiBx4ZTlkshWPJ7Je98gdKu0MFwQ6YVKu2oV5Z4UYDypfQ6RL3lc9lh6TelgwMZjPmygu7UXBgBK8Rncu9PyX77O1dKVyjol-oTSLbTtOmeRyq21rqjYzYldjf2NK5JV8CjmNHOU8ZWtyyYI3XhFe6qvw5WfxuedJOklvUplWT_wV-eVMvA8HPzvlQ9Re-Pgw8N1bDpCDZgdo_0f8MEWSl3mueHH4txgV0X_mmeF3UdjnU2zAmfvdr1ZYKeOn2KxLHLHvdQwx46DKd7soVSRL9ro5aE3Svpe3VvBy7hfeOALsJ-iAGFDuOHAjQMUg3AAuUj5vmJdGYEADnbmNCFKE0OM1rGgPOYsOEHNWT6DU4RZRANJAxPoUISGERFHRClppM1jYkXYGWq5UZl8VPCMST0g53_fvkG7_dFzOkkfB08XaK8SZzh14SVq2vGAK7SjPotsMb8u5_4bdhyqjg |
| 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%3Abook&rft.genre=proceeding&rft.title=2008+Canadian+Conference+on+Electrical+and+Computer+Engineering&rft.atitle=Reconstruction+of+handwritten+digit+images+using+autoencoder+neural+networks&rft.au=Tan%2C+C.C.&rft.au=Eswaran%2C+C.&rft.date=2008-05-01&rft.pub=IEEE&rft.isbn=9781424416424&rft.issn=0840-7789&rft.spage=000465&rft.epage=000470&rft_id=info:doi/10.1109%2FCCECE.2008.4564577&rft.externalDocID=4564577 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0840-7789&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0840-7789&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0840-7789&client=summon |