Extreme learning machine adapted to noise based on optimization algorithms
The extreme learning machine for neural networks of feedforward of a single hidden layer randomly assigns the weights of entry and analytically determines the weights the output by means the Moore-Penrose inverse, this algorithm tends to provide an extremely fast learning speed preserving the adjust...
- Autores:
-
Vásquez, A
Mora, M
Salazar, E
Gelvez, E
- Tipo de recurso:
- Fecha de publicación:
- 2020
- Institución:
- Universidad Simón Bolívar
- Repositorio:
- Repositorio Digital USB
- Idioma:
- eng
- OAI Identifier:
- oai:bonga.unisimon.edu.co:20.500.12442/6380
- Acceso en línea:
- https://hdl.handle.net/20.500.12442/6380
https://iopscience.iop.org/article/10.1088/1742-6596/1514/1/012006/pdf
- Palabra clave:
- Optimization algorithm
Moore-Penrose
Learning
- Rights
- openAccess
- License
- Attribution-NonCommercial-NoDerivatives 4.0 Internacional
| id |
USIMONBOL2_fe0ad17f06e0b9d8fb5a3eaf14dd5981 |
|---|---|
| oai_identifier_str |
oai:bonga.unisimon.edu.co:20.500.12442/6380 |
| network_acronym_str |
USIMONBOL2 |
| network_name_str |
Repositorio Digital USB |
| repository_id_str |
|
| dc.title.eng.fl_str_mv |
Extreme learning machine adapted to noise based on optimization algorithms |
| title |
Extreme learning machine adapted to noise based on optimization algorithms |
| spellingShingle |
Extreme learning machine adapted to noise based on optimization algorithms Optimization algorithm Moore-Penrose Learning |
| title_short |
Extreme learning machine adapted to noise based on optimization algorithms |
| title_full |
Extreme learning machine adapted to noise based on optimization algorithms |
| title_fullStr |
Extreme learning machine adapted to noise based on optimization algorithms |
| title_full_unstemmed |
Extreme learning machine adapted to noise based on optimization algorithms |
| title_sort |
Extreme learning machine adapted to noise based on optimization algorithms |
| dc.creator.fl_str_mv |
Vásquez, A Mora, M Salazar, E Gelvez, E |
| dc.contributor.author.none.fl_str_mv |
Vásquez, A Mora, M Salazar, E Gelvez, E |
| dc.subject.eng.fl_str_mv |
Optimization algorithm Moore-Penrose Learning |
| topic |
Optimization algorithm Moore-Penrose Learning |
| description |
The extreme learning machine for neural networks of feedforward of a single hidden layer randomly assigns the weights of entry and analytically determines the weights the output by means the Moore-Penrose inverse, this algorithm tends to provide an extremely fast learning speed preserving the adjustment levels achieved by classifiers such as multilayer perception and support vector machine. However, the Moore-Penrose inverse loses precision when using data with additive noise in training. That is why in this paper a method to robustness of extreme learning machine to additive noise proposed. The method consists in computing the weights of the output layer using non-linear optimization algorithms without restrictions. Tests are performed with the gradient descent optimization algorithm and with the Levenberg-Marquardt algorithm. From the implementation it is observed that through the use of these algorithms, smaller errors are achieved than those obtained with the Moore-Penrose inverse. |
| publishDate |
2020 |
| dc.date.accessioned.none.fl_str_mv |
2020-08-27T23:34:51Z |
| dc.date.available.none.fl_str_mv |
2020-08-27T23:34:51Z |
| dc.date.issued.none.fl_str_mv |
2020 |
| dc.type.coarversion.fl_str_mv |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| dc.type.coar.fl_str_mv |
http://purl.org/coar/resource_type/c_2df8fbb1 |
| dc.type.driver.eng.fl_str_mv |
info:eu-repo/semantics/article |
| dc.type.spa.spa.fl_str_mv |
Artículo científico |
| dc.identifier.issn.none.fl_str_mv |
17426588 |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/20.500.12442/6380 |
| dc.identifier.url.none.fl_str_mv |
https://iopscience.iop.org/article/10.1088/1742-6596/1514/1/012006/pdf |
| identifier_str_mv |
17426588 |
| url |
https://hdl.handle.net/20.500.12442/6380 https://iopscience.iop.org/article/10.1088/1742-6596/1514/1/012006/pdf |
| dc.language.iso.eng.fl_str_mv |
eng |
| language |
eng |
| dc.rights.*.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 Internacional |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| dc.rights.uri.*.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
| dc.rights.accessrights.eng.fl_str_mv |
info:eu-repo/semantics/openAccess |
| rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.mimetype.eng.fl_str_mv |
pdf |
| dc.publisher.eng.fl_str_mv |
IOP Publishing |
| dc.source.eng.fl_str_mv |
Journal of Physics: Conference Series |
| dc.source.none.fl_str_mv |
Vol. 1514 No. 1 (2020) |
| institution |
Universidad Simón Bolívar |
| bitstream.url.fl_str_mv |
https://bonga.unisimon.edu.co/bitstreams/8680aee8-26f0-48a9-babc-dac98dbc883d/download https://bonga.unisimon.edu.co/bitstreams/21af1537-b5ed-464a-ac75-fad43d59b2f3/download https://bonga.unisimon.edu.co/bitstreams/e93182d7-74a8-4b99-9ddb-2fa6bb7d6b8d/download https://bonga.unisimon.edu.co/bitstreams/2811ecff-01dd-4a72-99a2-a06176e22a5d/download https://bonga.unisimon.edu.co/bitstreams/2f8b86ea-60db-4d9d-b2ce-40cb99f3fad0/download |
| bitstream.checksum.fl_str_mv |
c09575f25cb6a6c9ad86f1dbe78f9eef 4460e5956bc1d1639be9ae6146a50347 733bec43a0bf5ade4d97db708e29b185 a9be7d42c2759cfe49ce50ef8246853a c1d0b0fbe66fdee34bba200bd929ebc6 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Digital Universidad Simón Bolívar |
| repository.mail.fl_str_mv |
repositorio.digital@unisimon.edu.co |
| _version_ |
1814076170944118784 |
| spelling |
Vásquez, Ad8f4cb05-84e7-4272-9e5f-5744834df75fMora, M630644e5-97cc-482b-b5d0-8f65851e3399Salazar, E986e187f-0d67-43f5-81cd-ec0b48cc4766Gelvez, Ed34b29f4-5323-4e58-83ca-7ae2e85e1ce02020-08-27T23:34:51Z2020-08-27T23:34:51Z202017426588https://hdl.handle.net/20.500.12442/6380https://iopscience.iop.org/article/10.1088/1742-6596/1514/1/012006/pdfThe extreme learning machine for neural networks of feedforward of a single hidden layer randomly assigns the weights of entry and analytically determines the weights the output by means the Moore-Penrose inverse, this algorithm tends to provide an extremely fast learning speed preserving the adjustment levels achieved by classifiers such as multilayer perception and support vector machine. However, the Moore-Penrose inverse loses precision when using data with additive noise in training. That is why in this paper a method to robustness of extreme learning machine to additive noise proposed. The method consists in computing the weights of the output layer using non-linear optimization algorithms without restrictions. Tests are performed with the gradient descent optimization algorithm and with the Levenberg-Marquardt algorithm. From the implementation it is observed that through the use of these algorithms, smaller errors are achieved than those obtained with the Moore-Penrose inverse.pdfengIOP PublishingAttribution-NonCommercial-NoDerivatives 4.0 Internacionalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Journal of Physics: Conference SeriesVol. 1514 No. 1 (2020)Optimization algorithmMoore-PenroseLearningExtreme learning machine adapted to noise based on optimization algorithmsinfo:eu-repo/semantics/articleArtículo científicohttp://purl.org/coar/version/c_970fb48d4fbd8a85http://purl.org/coar/resource_type/c_2df8fbb1Al-Shayea Q K 2011 Artificial neural networks in medical diagnosis International Journal of Computer Science Issues 8(2) 150Melin P, Urias J, Solano D, Soto M, Lopez M and Castillo O 2006 Voice Recognition with Neural Networks, Type-2 Fuzzy Logic and Genetic Algorithms Engineering Letters 13(2) 108Suresh S, Babu R V and Kim H J 2009 No-reference image quality assessment using modified extreme learning machine classifier Applied Soft Computing 9(2) 541Mohammed A A, Minhas R, Wu Q J and Sid-Ahmed M A 2011 Human face recognition based on multidimensional PCA and extreme learning machine Pattern Recognition 44 2588Bai Z, Huang G B, Wang D, Wang H and Westover M B 2014 Sparse extreme learning machine for classification IEEE Transactions on Cybernetics 44 1858Huang G, Song S, Gupta J N and Wu C 2014 Semi-supervised and unsupervised extreme learning machines IEEE Transactions on Cybernetics 44 2405Huang G B, Zhou H, Ding X and Zhang R 2011 Extreme learning machine for regression and multiclass classification IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 42 513Huang Z, Yu Y, Gu J and Liu H 2016 An efficient method for traffic sign recognition based on extreme learning machine IEEE Transactions on Cybernetics 47 920Huang G B, Zhu Q Y and Siew C K 2004 Extreme learning machine: a new learning scheme of feedforward neural networks Neural Networks 2 985Huang G B, Chen L and Siew C K 2006 Universal approximation using incremental constructive feedforward networks with random hidden nodes IEEE Trans. Neural Networks 17 879Arnold D V and Beyer H G 2003 A comparison of evolution strategies with other direct search methods in the presence of noise Computational Optimization and ApplicationsCantú-Paz E 2004 Adaptive sampling for noisy problems Genetic and Evolutionary Computation-GECCO 2004 3102 947Ridout D and Judd K 2002 Convergence properties of gradient descent noise reduction Physica D: Nonlinear Phenomena 165 26Courrieu P 2008 Fast computation of Moore-Penrose inverse matrices Neural Information Processing - Letters and Reviews 8 25Ranganathan A 2004 The levenberg-marquardt algorithm Tutoral on LM algorithm 11 101Yu H and Wilamowski B M 2011 Levenberg-marquardt training Industrial electronics handbook 5 1Gavin H 2013 The Levenberg-Marquardt method for nonlinear least squares curve-fitting problems (Durham: Duke University) 1Huang G B and Babri H A 1998 Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions IEEE Transactions on Neural Networks 9 224Huang G B 2003 Learning capability and storage capacity of two-hidden-layer feedforward networks IEEE Transactions on Neural Networks 14 274Tamura S I and Tateishi M 1997 Capabilities of a four-layered feedforward neural network: four layers versus three IEEE Transactions on Neural Networks 8 251ORIGINALPDF.pdfPDF.pdfPDFapplication/pdf774647https://bonga.unisimon.edu.co/bitstreams/8680aee8-26f0-48a9-babc-dac98dbc883d/downloadc09575f25cb6a6c9ad86f1dbe78f9eefMD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805https://bonga.unisimon.edu.co/bitstreams/21af1537-b5ed-464a-ac75-fad43d59b2f3/download4460e5956bc1d1639be9ae6146a50347MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-8381https://bonga.unisimon.edu.co/bitstreams/e93182d7-74a8-4b99-9ddb-2fa6bb7d6b8d/download733bec43a0bf5ade4d97db708e29b185MD53TEXTPDF.pdf.txtPDF.pdf.txtExtracted texttext/plain20136https://bonga.unisimon.edu.co/bitstreams/2811ecff-01dd-4a72-99a2-a06176e22a5d/downloada9be7d42c2759cfe49ce50ef8246853aMD54THUMBNAILPDF.pdf.jpgPDF.pdf.jpgGenerated Thumbnailimage/jpeg1395https://bonga.unisimon.edu.co/bitstreams/2f8b86ea-60db-4d9d-b2ce-40cb99f3fad0/downloadc1d0b0fbe66fdee34bba200bd929ebc6MD5520.500.12442/6380oai:bonga.unisimon.edu.co:20.500.12442/63802024-08-14 21:54:45.718http://creativecommons.org/licenses/by-nc-nd/4.0/Attribution-NonCommercial-NoDerivatives 4.0 Internacionalopen.accesshttps://bonga.unisimon.edu.coRepositorio Digital Universidad Simón Bolívarrepositorio.digital@unisimon.edu.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 |