File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/IJCNN.2003.1223693
- Scopus: eid_2-s2.0-0141794666
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Acceleration of Levenberg-Marquardt Training of Neural Networks with Variable Decay Rate
Title | Acceleration of Levenberg-Marquardt Training of Neural Networks with Variable Decay Rate |
---|---|
Authors | |
Keywords | Computers Computer networks |
Issue Date | 2003 |
Publisher | IEEE. |
Citation | Proceedings Of The International Joint Conference On Neural Networks, 2003, v. 3, p. 1873-1878 How to Cite? |
Abstract | In the application of the standard Levenherg-Marquardt training process of neural networks, error oscillations are frequently observed and they usually aggravate on approaching the required accuracy. In this paper, a modified Levenberg-Marquardt method based on variable decay rate in each iteration is proposed in order to reduce such error oscillations. Through a certain variation of the decay rate, the time required for training of neural networks is cut down to less than half of that required in the standard Levenberg-Marquardt method. Several numerical examples are given to show the effectiveness of the proposed method. |
Persistent Identifier | http://hdl.handle.net/10722/47064 |
ISSN | |
References |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, TC | en_HK |
dc.contributor.author | Han, DJ | en_HK |
dc.contributor.author | Au, FTK | en_HK |
dc.contributor.author | Tham, LG | en_HK |
dc.date.accessioned | 2007-10-30T07:05:54Z | - |
dc.date.available | 2007-10-30T07:05:54Z | - |
dc.date.issued | 2003 | en_HK |
dc.identifier.citation | Proceedings Of The International Joint Conference On Neural Networks, 2003, v. 3, p. 1873-1878 | en_HK |
dc.identifier.issn | 1098-7576 | en_HK |
dc.identifier.uri | http://hdl.handle.net/10722/47064 | - |
dc.description.abstract | In the application of the standard Levenherg-Marquardt training process of neural networks, error oscillations are frequently observed and they usually aggravate on approaching the required accuracy. In this paper, a modified Levenberg-Marquardt method based on variable decay rate in each iteration is proposed in order to reduce such error oscillations. Through a certain variation of the decay rate, the time required for training of neural networks is cut down to less than half of that required in the standard Levenberg-Marquardt method. Several numerical examples are given to show the effectiveness of the proposed method. | en_HK |
dc.format.extent | 305430 bytes | - |
dc.format.extent | 1760 bytes | - |
dc.format.extent | 2058 bytes | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | text/plain | - |
dc.format.mimetype | text/plain | - |
dc.language | eng | en_HK |
dc.publisher | IEEE. | en_HK |
dc.relation.ispartof | Proceedings of the International Joint Conference on Neural Networks | en_HK |
dc.rights | ©2003 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. | - |
dc.subject | Computers | en_HK |
dc.subject | Computer networks | en_HK |
dc.title | Acceleration of Levenberg-Marquardt Training of Neural Networks with Variable Decay Rate | en_HK |
dc.type | Conference_Paper | en_HK |
dc.identifier.openurl | http://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1098-7576&volume=3&spage=1873&epage=1878&date=2003&atitle=Acceleration+of+Levenberg-Marquardt+training+of+neural+networks+with+variable+decay+rate | en_HK |
dc.identifier.email | Au, FTK:francis.au@hku.hk | en_HK |
dc.identifier.email | Tham, LG:hrectlg@hkucc.hku.hk | en_HK |
dc.identifier.authority | Au, FTK=rp00083 | en_HK |
dc.identifier.authority | Tham, LG=rp00176 | en_HK |
dc.description.nature | published_or_final_version | en_HK |
dc.identifier.doi | 10.1109/IJCNN.2003.1223693 | en_HK |
dc.identifier.scopus | eid_2-s2.0-0141794666 | en_HK |
dc.identifier.hkuros | 93063 | - |
dc.relation.references | http://www.scopus.com/mlt/select.url?eid=2-s2.0-0141794666&selection=ref&src=s&origin=recordpage | en_HK |
dc.identifier.volume | 3 | en_HK |
dc.identifier.spage | 1873 | en_HK |
dc.identifier.epage | 1878 | en_HK |
dc.identifier.scopusauthorid | Chen, TC=16634751900 | en_HK |
dc.identifier.scopusauthorid | Han, DJ=7403219487 | en_HK |
dc.identifier.scopusauthorid | Au, FTK=7005204072 | en_HK |
dc.identifier.scopusauthorid | Tham, LG=7006213628 | en_HK |
dc.identifier.issnl | 1098-7576 | - |