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 2/2020

24.10.2019

A Smoothing Algorithm with Constant Learning Rate for Training Two Kinds of Fuzzy Neural Networks and Its Convergence

verfasst von: Long Li, Zhijun Qiao, Zuqiang Long

Erschienen in: Neural Processing Letters | Ausgabe 2/2020

Einloggen

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

search-config
loading …

Abstract

In this paper, a smoothing algorithm with constant learning rate is presented for training two kinds of fuzzy neural networks (FNNs): max-product and max-min FNNs. Some weak and strong convergence results for the algorithm are provided with the error function monotonically decreasing, its gradient going to zero, and weight sequence tending to a fixed value during the iteration. Furthermore, conditions for the constant learning rate are specified to guarantee the convergence. Finally, three numerical examples are given to illustrate the feasibility and efficiency of the algorithm and to support the theoretical findings.
Vorheriger Artikel Multi-layer Adaptive Feature Fusion for Semantic Segmentation
Nächster Artikel Mutual Improvement Between Temporal Ensembling and Virtual Adversarial Training

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
Anhänge
Nur mit Berechtigung zugänglich
Literatur
1.
Baruch IS, Lopez RB, Guzman J-LO, Flores JM (2008) A fuzzy-neural multi-model for nonlinear systems identification and control. Fuzzy Sets Syst 159:2650–2667MathSciNetCrossRef
2.
Hengjie S, Chunyan M, Zhiqi S, Yuan M, Lee B-S (2009) A fuzzy neural network with fuzzy impact grades. Neurocomputing 72:3098–3122CrossRef
3.
Castro JR, Castillo O, Melin P, Rodríguez-Díaz A (2009) A hybrid learning algorithm for a class of interval type-2 fuzzy neural networks. Inf Sci 179:2175–2193CrossRef
4.
Juang C-F, Yang-YinLin, Chiu-ChuanTu (2010) A recurrent self-evolving fuzzy neural network with local feedbacks and itsapplication to dynamic system processing. Fuzzy Sets Syst 161:2552–2568CrossRef
5.
Khajeh A, Modarress H (2010) Prediction of solubility of gases in polystyrene by adaptive neuro-fuzzy inference system and radial basis function neural network. Expert Syst Appl 37:3070–3074CrossRef
6.
Nandedkar AV, Biswas PK (2007) A fuzzy min-max neural network classifier with compensatory neuron architecture. IEEE Trans Neural Netw 18:42–54CrossRef
7.
Sonule PM, Shetty BS (2017) An enhanced fuzzy min-max neural network with ant colony optimization based-rule-extractor for decision making. Neurocomputing 239:204–213CrossRef
8.
Peeva K (2013) Resolution of fuzzy relational equations-method, algorithm and software with applications. Inf Sci 234(10):44–63MathSciNetCrossRef
9.
Brouwer RK (2002) A discrete fully recurrent network of max product units for associative memory and classification. Int J Neural Syst 12(3–4):247–262CrossRef
10.
Wong W-K, Loo C-K, Lim W-S, Tan P-N (2010) Thermal condition monitoring system using log-polar mapping, quaternion correlation and max-product fuzzy neural network classification. Neurocomputing 74(1–3):164–177CrossRef
11.
Li Y, Zhong-Fu W (2008) Fuzzy feature selection based on min-max learning rule and extension matrix. Pattern Recognit 41:217–226CrossRef
12.
Wong W, Loo C, Lim W, Tan P (2010) Thermal condition monitoring system using log-polar mapping, quaternion correlation and max-product fuzzy neural network classification. Neurocomputing 74:164–177CrossRef
13.
Liu J, Ma Y, Zhang H, Hanguang S, Xiao G (2017) A modified fuzzy minCmax neural network for data clustering and its application on pipeline internal inspection data. Neurocomputing 238:56–66CrossRef
14.
Mohammeda MF, Lim CP (2017) A new hyperbox selection rule and a pruning strategy for the enhanced fuzzy min-max neural network. Neural Netw 86:69–79CrossRef
15.
Shindea S, Kulkarni U (2016) Extracting classification rules from modified fuzzy minCmax neuralnetwork for data with mixed attributes. Appl Soft Comput 40:364–378CrossRef
16.
Quteishat A, Lim CP (2008) A modified fuzzy min-max neural network with rule extraction and its application to fault detection and classification. Appl Soft Comput 8:985–995CrossRef
17.
Park J-H, Kim T-H, Sugie T (2011) Output feedback model predictive control for LPV systems based on quasi-min-max algorithm. Automatica 47:2052–2058MathSciNetCrossRef
18.
Iliadis LS, Spartalis S, Tachos S (2008) Application of fuzzy T-norms towards a new artificial neural networks? Evaluation framework: a case from wood industry. Inf Sci 178:3828–3839CrossRef
19.
Marks RJ II, Oh S, Arabshahi P, Caudell TP, Choi JJ, Song BG (1992) Steepest descent adaptation of min-max fuzzy if-then rules. In: Proc. IJCNN, Beijing, China, vol. III, pp 471–477
20.
21.
Nikov A, Stoeva S (2001) Quick fuzzy backpropagation algorithm. Neural Netw 14:231–244CrossRef
22.
Blanco A, Delgado M, Requena I (1995) Identification of fuzzy relational equations by fuzzy neural networks. Fuzzy Sets Syst 71:215–226CrossRef
23.
Zhang X, Hang C-C (1996) The min-max function differentiation and training of fuzzy neural networks. IEEE Trans Neural Netw 7(5):1139–1149CrossRef
24.
Li L, Qiao Z, Liu Y, Chen Y (2017) A convergent smoothing algorithm for training max-min fuzzy neural networks. Neurocomputing 260:404–410CrossRef
25.
Peng J-M, Lin Z (1999) A non-interior continuation method for generalized linear complementarity problems. Math Program Ser A 86:533–563MathSciNetCrossRef
26.
Tong X, Qi L, Felix W, Zhou H (2010) A smoothing method for solving portfolio optimization with CVaR and applications in allocation of generation asset. Appl Math Comput 216:1723–1740MathSciNetMATH
27.
Zhang H, Wu W, Liu F, Yao M (2009) Boundedness and convergence of online gradient method with penalty for feedforward neural networks. IEEE Trans Neural Netw 20:1050–1054CrossRef
28.
Wei W, Li L, Yang J, Liu Y (2010) A modified gradient-based neuro-fuzzy learning algorithm and its convergence. Inf Sci 180:1630–1642CrossRef
29.
Shao HM, Zheng GF (2011) Boundedness and convergence of online gradient method with penalty and momentum. Neurocomputing 74:765C770
30.
Loetamonphong J, Fang S-C (1999) An efficient solution procedure for fuzzy relation equations with max-product composition. IEEE Trans Fuzzy Syst 7:441–445CrossRef
31.
32.
Wang J, Wei W, Zurada JM (2011) Determinisitc convergence of conjugate gradient method for feedforward neural networks. Neurocomputing 74:2368–2376CrossRef
Metadaten
Titel
A Smoothing Algorithm with Constant Learning Rate for Training Two Kinds of Fuzzy Neural Networks and Its Convergence
verfasst von
Long Li
Zhijun Qiao
Zuqiang Long
Publikationsdatum
24.10.2019
Verlag
Springer US
Erschienen in
Neural Processing Letters / Ausgabe 2/2020
Print ISSN: 1370-4621
Elektronische ISSN: 1573-773X
DOI
https://doi.org/10.1007/s11063-019-10135-4

Weitere Artikel der Ausgabe 2/2020

Neural Processing Letters 2/2020 Zur Ausgabe

OriginalPaper

An Image Clustering Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids and MMD Distance

OriginalPaper

Almost Automorphic Solutions in Distribution Sense of Quaternion-Valued Stochastic Recurrent Neural Networks with Mixed Time-Varying Delays

OriginalPaper

Attention-Based Generative Adversarial Network for Semi-supervised Image Classification

OriginalPaper

Joint Robust Transfer Metric and Adaptive Transfer Function Learning

OriginalPaper

Community Detection in Complex Networks Using Nonnegative Matrix Factorization and Density-Based Clustering Algorithm

OriginalPaper

Multi-layer Adaptive Feature Fusion for Semantic Segmentation

Neuer Inhalt

    Bildnachweise