Extreme learning machine adapted to noise based on optimization algorithms
| datacite.rights | http://purl.org/coar/access_right/c_abf2 | eng |
| dc.contributor.author | Vásquez, A | |
| dc.contributor.author | Mora, M | |
| dc.contributor.author | Salazar, E | |
| dc.contributor.author | Gelvez, E | |
| dc.date.accessioned | 2020-08-27T23:34:51Z | |
| dc.date.available | 2020-08-27T23:34:51Z | |
| dc.date.issued | 2020 | |
| dc.description.abstract | 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. | eng |
| dc.format.mimetype | eng | |
| dc.identifier.issn | 17426588 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12442/6380 | |
| dc.identifier.url | https://iopscience.iop.org/article/10.1088/1742-6596/1514/1/012006/pdf | |
| dc.language.iso | eng | eng |
| dc.publisher | IOP Publishing | eng |
| dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | eng |
| dc.rights.accessrights | info:eu-repo/semantics/openAccess | eng |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | |
| dc.source | Journal of Physics: Conference Series | eng |
| dc.source | Vol. 1514 No. 1 (2020) | |
| dc.subject | Optimization algorithm | eng |
| dc.subject | Moore-Penrose | eng |
| dc.subject | Learning | eng |
| dc.title | Extreme learning machine adapted to noise based on optimization algorithms | eng |
| dc.type.driver | info:eu-repo/semantics/article | eng |
| dc.type.spa | Artículo científico | spa |
| dcterms.references | Al-Shayea Q K 2011 Artificial neural networks in medical diagnosis International Journal of Computer Science Issues 8(2) 150 | eng |
| dcterms.references | Melin 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) 108 | eng |
| dcterms.references | Suresh 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) 541 | eng |
| dcterms.references | Mohammed 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 2588 | eng |
| dcterms.references | Bai Z, Huang G B, Wang D, Wang H and Westover M B 2014 Sparse extreme learning machine for classification IEEE Transactions on Cybernetics 44 1858 | eng |
| dcterms.references | Huang G, Song S, Gupta J N and Wu C 2014 Semi-supervised and unsupervised extreme learning machines IEEE Transactions on Cybernetics 44 2405 | eng |
| dcterms.references | Huang 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) 42 513 | eng |
| dcterms.references | Huang 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 47 920 | eng |
| dcterms.references | Huang G B, Zhu Q Y and Siew C K 2004 Extreme learning machine: a new learning scheme of feedforward neural networks Neural Networks 2 985 | eng |
| dcterms.references | Huang G B, Chen L and Siew C K 2006 Universal approximation using incremental constructive feedforward networks with random hidden nodes IEEE Trans. Neural Networks 17 879 | eng |
| dcterms.references | Arnold 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 Applications | eng |
| dcterms.references | Cantú-Paz E 2004 Adaptive sampling for noisy problems Genetic and Evolutionary Computation-GECCO 2004 3102 947 | eng |
| dcterms.references | Ridout D and Judd K 2002 Convergence properties of gradient descent noise reduction Physica D: Nonlinear Phenomena 165 26 | eng |
| dcterms.references | Courrieu P 2008 Fast computation of Moore-Penrose inverse matrices Neural Information Processing - Letters and Reviews 8 25 | eng |
| dcterms.references | Ranganathan A 2004 The levenberg-marquardt algorithm Tutoral on LM algorithm 11 101 | eng |
| dcterms.references | Yu H and Wilamowski B M 2011 Levenberg-marquardt training Industrial electronics handbook 5 1 | eng |
| dcterms.references | Gavin H 2013 The Levenberg-Marquardt method for nonlinear least squares curve-fitting problems (Durham: Duke University) 1 | eng |
| dcterms.references | Huang 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 9 224 | eng |
| dcterms.references | Huang G B 2003 Learning capability and storage capacity of two-hidden-layer feedforward networks IEEE Transactions on Neural Networks 14 274 | eng |
| dcterms.references | Tamura S I and Tateishi M 1997 Capabilities of a four-layered feedforward neural network: four layers versus three IEEE Transactions on Neural Networks 8 251 | eng |
| oaire.version | info:eu-repo/semantics/publishedVersion | eng |