Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben
Neural Processing Letters
Erschienen in: Neural Processing Letters 2/2016

01.10.2016

Architecture Selection of ELM Networks Based on Sensitivity of Hidden Nodes

verfasst von: Junhai Zhai, Qingyan Shao, Xizhao Wang

Erschienen in: Neural Processing Letters | Ausgabe 2/2016

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Extreme learning machine (ELM) was proposed as a new algorithm for training single-hidden layer feed-forward neural networks (SLFNs). One of the issues in EML is how to determine the architecture of SLFNs. Based on sensitivity of hidden nodes, an approach of architecture selection of ELM networks by applying a pruned method was proposed in this paper. The proposed pruning method utilizes sensitivity to measure the significance of hidden nodes. Beginning from an initial large number of hidden nodes, the insignificant nodes with lower sensitivity are then pruned. Experimental results on ten UCI data sets show that the proposed approach can obtain compact network architecture that generate comparable prediction accuracy on unseen samples.
Vorheriger Artikel Hierarchical Parallel Genetic Optimization Fuzzy ARTMAP Ensemble
Nächster Artikel A Study on Multi-Scale Kernel Optimisation via Centered Kernel-Target Alignment

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Jetzt informieren
Literatur
1.
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501CrossRef
2.
Huang GB, Wang DH, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cybern 2:107–122CrossRef
3.
Huang GB, Chen L, Siew CK (2006) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17:879–892CrossRef
4.
Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20:273–297MATH
5.
Haykin S (1999) Neural networks: a comprehensive foundation. Prentice Hall, New Jersey, pp 178–228MATH
6.
Battiti R (1992) First and second order methods for learning: between the steepest descent and Newton’s method. Neural Comput 2:141–166CrossRef
7.
LeCun Y, Denker JS, Solla SA (1990) Optimal brain damage. In: Touretzky DS (ed) Advances in neural information processing systems, vol 2. Morgan Kaufmann Publishers Inc., San Francisco, pp 598–605
8.
Hassibi B, Stork DG, Wolff GJ (1993) Optimal brain surgeon and general network pruning. In: IEEE international conference on neural networks, 28 March–1 April 1993, San Francisco, CA, vol 1, pp 293–299
9.
Monari G, Dreyfus G (2002) Local overfitting control via leverages. Neural Comput 6:1481–1506CrossRefMATH
10.
Feng G, Huang GB, Lin Q, Gay R (2009) Error minimized extreme learning machine with growth of hidden nodes and incremental learning. IEEE Trans Neural Networks 20:1352–1357CrossRef
11.
Lan Y, Soh YC, Huang GB (2010) Constructive hidden nodes selection of extreme learning machine for regression. Neurocomputing 73:3191–3199CrossRef
12.
Huang GB, Li MB, Chen L, Siew CK (2008) Incremental extreme learning machine with fully complex hidden nodes. Neurocomputing 71:576–583CrossRef
13.
Huang GB, Chen L (2008) Enhanced random search based incremental extreme learning machine. Neurocomputing 71:3060–3068
14.
Huang GB, Chen L (2007) Convex incremental extreme learning machine. Neurocomputing 70:3056–3062CrossRef
15.
Rong HJ, Ong YS, Tan AH, Zhu Z (2008) A fast pruned-extreme learning machine for classification problem. Neurocomputing 72:359–366CrossRef
16.
Miche Y, Sorjamaa A, Bas P, Simula O (2010) OP-ELM: optimally pruned extreme learning machine. IEEE Trans Neural Networks 21:158–162CrossRef
17.
Akaike H (1973) Information theory and an extension of the maximum likelihood principle. In: Petrov BN, Csaki F (eds) Second international symposium on information theory. Academiai Kiado, Budapest, pp 267–281
18.
Similä T, Tikka J (2005) Multiresponse sparse regression with application to multidimensional scaling. Proc Int Conf Artif Neural Netw 3697/2005:97–102
19.
20.
Myers RH (1990) Classical and modern regression with applications, 2nd edn. Duxbury, Pacific Grove
21.
Andrs BC, Pedro JGL, Jos-Luis SG (2013) Neural architecture design based on extreme learning machine. Neural Netw 48:19–24CrossRef
22.
Wang X, Shao Q, Qi M, Zhai J (2013) Architecture selection for networks trained with extreme learning machine using localized generalization error model. Neurocomputing 102:1–9CrossRef
23.
Deng W, Zheng Q, Chen L (2009) Regularized extrem learning machine. In: IEEE symposiumon computational intelligence and data mining, 30 March–2 April 2009, Nashville, TN, pp 389–395
24.
Shao H, Japkowicz N (2012) Applying least angle regression to ELM. In: Kosseim L, Inkpen D (eds) Canadian AI, LNAI 7310. pp 170–180
25.
Miche Y, Heeswijk M, Bas P, Simula O, Lendasse A (2011) TROP-ELM: a double-regularized ELM using LARS and Tikhonov regularization. Neurocomputing 74:2413–2421CrossRef
26.
Hoerl AE, Kennard R (1970) Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12:55–67CrossRefMATH
27.
Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Ser B 58:267–288MathSciNetMATH
28.
29.
Neumann K, Steil JJ (2013) Optimizing extreme learning machines via ridge regression and batch intrinsic plasticity. Neurocomputing 102:23–30CrossRef
30.
Liao SZ, Feng C (2014) Meta-ELM: ELM with ELM hidden nodes. Neurocomputing 128:81–87CrossRef
31.
Ahila R, Sadasivam V, Manimala K (2015) An integrated PSO for parameter determination and feature selection of ELM and its application in classification of power system disturbances. Appl Soft Comput 32:23–37CrossRef
32.
Tavares LD, Saldanha RR, Vieira DAG (2015) Extreme learning machine with parallel layer perceptrons. Neurocomputing 166:164–171CrossRef
33.
Yang JB, Shen KQ, Ong CJ (2009) Feature selection for MLP neural network: the use of random permutation of probabilistic outputs. IEEE Trans Neural Netw 20:1911–1922CrossRef
34.
Huang GB (2003) Learning capability and storage capacity of two-hidden-layer feedforward networks. IEEE Trans Neural Netw 14:274–281CrossRef
35.
Serre D (2002) Matrices: theory and applications. Springer, New YorkMATH
36.
Bishop CM (1996) Neural networks for pattern recognition. Clarendon Press, Oxford, pp 129–168MATH
37.
Mallows CL (2000) Some comments on \(C_p\). Technometrics 42:87–94
38.
Yan X, Su XG (2009) Linear regression analysis: theory and computing. World Scientific Publishing Co. Pte. Ltd., SingaporeCrossRefMATH
39.
Liu X, Gao C, Li P (2012) A comparative analysis of support vector machines and extreme learning machines. Neural Netw 33:58–66CrossRefMATH
40.
Golub G, Charles F, Loan V (1983) Matrix computations. Johns Hopkins University Press, BaltimoreMATH
41.
Khan JA, Aelst SV, Zamara RH (2007) Robust linear model selection based on least angle regression. J Am Stat Assoc 102:1289–1299MathSciNetCrossRefMATH
42.
Dougherty J, Kohavi R, Sahami M (1995) Supervised and unsupervised discretization of continuous features. In: Proceedings of the twelfth international conference. Morgan Kaufmann Publishers, San Francisco, pp 194–202
43.
44.
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer, New YorkCrossRefMATH
45.
Janez D (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30MathSciNetMATH
Metadaten
Titel
Architecture Selection of ELM Networks Based on Sensitivity of Hidden Nodes
verfasst von
Junhai Zhai
Qingyan Shao
Xizhao Wang
Publikationsdatum
01.10.2016
Verlag
Springer US
Erschienen in
Neural Processing Letters / Ausgabe 2/2016
Print ISSN: 1370-4621
Elektronische ISSN: 1573-773X
DOI
https://doi.org/10.1007/s11063-015-9470-1

Weitere Artikel der Ausgabe 2/2016

Neural Processing Letters 2/2016 Zur Ausgabe

OriginalPaper

Bifurcation Analysis in a Three-Neuron Artificial Neural Network Model with Distributed Delays

OriginalPaper

Hierarchical Parallel Genetic Optimization Fuzzy ARTMAP Ensemble

OriginalPaper

A Complex-valued Encoding Bat Algorithm for Solving 0–1 Knapsack Problem

BriefCommunication

Steganography of Digital Watermark Based on Artificial Neural Networks in Image Communication and Intellectual Property Protection

OriginalPaper

Dissipativity and Passivity Analysis of Markovian Jump Neural Networks with Two Additive Time-Varying Delays

OriginalPaper

On the Use of Nominal and Ordinal Classifiers for the Discrimination of States of Development in Fish Oocytes

Neuer Inhalt

    Bildnachweise