Gauss-Newton approximation to Bayesian learning
This paper describes the application of Bayesian regularization to the training of feedforward neural networks. A Gauss-Newton approximation to the Hessian matrix, which can be conveniently implemented within the framework of the Levenberg-Marquardt algorithm, is used to reduce the computational ove...
Saved in:
| Published in | 1997 IEEE International Conference on Neural Networks Vol. 3; pp. 1930 - 1935 vol.3 |
|---|---|
| Main Authors | , |
| Format | Conference Proceeding |
| Language | English Japanese |
| Published |
IEEE
1997
|
| Subjects | |
| Online Access | Get full text |
| ISBN | 0780341228 9780780341227 |
| DOI | 10.1109/ICNN.1997.614194 |
Cover
| Abstract | This paper describes the application of Bayesian regularization to the training of feedforward neural networks. A Gauss-Newton approximation to the Hessian matrix, which can be conveniently implemented within the framework of the Levenberg-Marquardt algorithm, is used to reduce the computational overhead. The resulting algorithm is demonstrated on a simple test problem and is then applied to three practical problems. The results demonstrate that the algorithm produces networks which have excellent generalization capabilities. |
|---|---|
| AbstractList | This paper describes the application of Bayesian regularization to the training of feedforward neural networks. A Gauss-Newton approximation to the Hessian matrix, which can be conveniently implemented within the framework of the Levenberg-Marquardt algorithm, is used to reduce the computational overhead. The resulting algorithm is demonstrated on a simple test problem and is then applied to three practical problems. The results demonstrate that the algorithm produces networks which have excellent generalization capabilities. |
| Author | Hagan, M.T. Dan Foresee, F. |
| Author_xml | – sequence: 1 givenname: F. surname: Dan Foresee fullname: Dan Foresee, F. organization: Lucent Technol., Oklahoma City, OK, USA – sequence: 2 givenname: M.T. surname: Hagan fullname: Hagan, M.T. |
| BookMark | eNotj8FOwzAQRC0BErT0jjjlB5J6bSf2HiGCUqkKFzhXm3qDjIoTxUHQvydSmctoLm9mFuIy9pGFuANZAEhcb-umKQDRFhUYQHMhFtI6qQ0o5a7FKqVPOcuUBiu8EesNfaeUN_wz9TGjYRj73_BFU5jT1GePdOIUKGZHpjGG-HErrjo6Jl79-1K8Pz-91S_57nWzrR92eYBST3nFFt1c6Xxbsu28sp1pW2xL45RC0u3BAmgPCt2BrfUEhshWQIoIOy_1UtyfuYGZ98M4bxpP-_Ml_Qff2UMm |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/ICNN.1997.614194 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings Accès INSA - IEEE Xplore POP ALL IEEE Xplore All Conference Proceedings IEEE Xplore IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EndPage | 1935 vol.3 |
| ExternalDocumentID | 614194 |
| GroupedDBID | 6IE 6IK 6IL AAJGR AAWTH ACGHX ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK OCL RIE RIL |
| ID | FETCH-LOGICAL-i153t-6e7984128db5e7fd27f4bb9b548229a3bc7113d1298ce77da14aa761a2aa9fd03 |
| IEDL.DBID | RIE |
| ISBN | 0780341228 9780780341227 |
| IngestDate | Tue Aug 26 18:26:10 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English Japanese |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i153t-6e7984128db5e7fd27f4bb9b548229a3bc7113d1298ce77da14aa761a2aa9fd03 |
| ParticipantIDs | ieee_primary_614194 |
| PublicationCentury | 1900 |
| PublicationDate | 19970000 |
| PublicationDateYYYYMMDD | 1997-01-01 |
| PublicationDate_xml | – year: 1997 text: 19970000 |
| PublicationDecade | 1990 |
| PublicationTitle | 1997 IEEE International Conference on Neural Networks |
| PublicationTitleAbbrev | ICNN |
| PublicationYear | 1997 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0000454969 |
| Score | 1.6008475 |
| Snippet | This paper describes the application of Bayesian regularization to the training of feedforward neural networks. A Gauss-Newton approximation to the Hessian... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1930 |
| SubjectTerms | Application software Bayesian methods Cities and towns Computer networks Feedforward neural networks Least squares methods Neural networks Newton method Recursive estimation Testing |
| Title | Gauss-Newton approximation to Bayesian learning |
| URI | https://ieeexplore.ieee.org/document/614194 |
| Volume | 3 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwELZoJyZeRbyVgdVp4rg5e6WiFCQqBip1q3y2gyqkFtFEAn49fqQgEAOb4yHKKdZ99_D3HSGXyNGhugGKOjeUl8JQiUxTJQX6I1KJMDrhflKOp_xuNpi1OtuBC2OtDZfPbOqXoZdvVrrxpbK-gxKXc3dIB0QZqVpf5RSvJCdLGRJzkTnXzJho9XU2z7DpUmayfzucTDxRD9L4zh-zVQK0jHYiZ3sdFAn9jZLntKkx1R-_9Br_-dW7pPfN4UsevtBpj2zZ5QHp36hmvabOs7mQLwl64m-LSF5M6lVypd6tJ1Um7SyJpx6Zjq4fh2PajkygC-e6alpakMIZKwwOLFSGQcURJbq8hDGpCtSQ54VxIC-0BTAq50pBmSumlKxMVhyS7nK1tEck0bxQqiosRwVco5ZaWuMbj8JFgJmGY7LvbZ2_RFWMeTTz5M_dU7IdZV996eKMdOvXxp47MK_xIvzGTx6Rm2E |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV05T8MwFLagDDBxFXGTgdVpDie2VypKC23E0ErdKj_bQQipRTSRgF-Pj7QIxMDmeIjyFOt97_D3PYSugYBBdUUxyFhhkjOFOSQSC87AHpGSudEJoyLvT8j9NJs2OtuOC6O1dpfPdGiXrpevFrK2pbKOgRKTc2-irYwQknmy1rqgYrXkeM5das4i45yThDUKO6tnuupTRrwz6BaFperR0L_1x3QVBy69Xc_aXjpNQnun5CWsKwjl5y_Fxn9-9x5qf7P4gsc1Pu2jDT0_RJ07US-X2Pg2E_QFTlH8_dnTF4NqEdyID21plUEzTeKpjSa923G3j5uhCfjZOK8K55pyZoxlCjJNS5XQkgBwMJlJknCRgqRxnCoD80xqSpWIiRA0j0UiBC9VlB6h1nwx18cokCQVokw1AUGJBMkl18q2HpmJASNJT9CBtXX26nUxZt7M0z93r9B2fzwazoaD4uEM7XgRWFvIOEet6q3WFwbaK7h0v_QLeB-erg |
| 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=1997+IEEE+International+Conference+on+Neural+Networks&rft.atitle=Gauss-Newton+approximation+to+Bayesian+learning&rft.au=Dan+Foresee%2C+F.&rft.au=Hagan%2C+M.T.&rft.date=1997-01-01&rft.pub=IEEE&rft.isbn=9780780341227&rft.volume=3&rft.spage=1930&rft.epage=1935+vol.3&rft_id=info:doi/10.1109%2FICNN.1997.614194&rft.externalDocID=614194 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780780341227/lc.gif&client=summon&freeimage=true |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780780341227/mc.gif&client=summon&freeimage=true |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780780341227/sc.gif&client=summon&freeimage=true |