nach oben

Neural Computing and Applications

Erschienen in:

01.06.2008 | Original Article

A hybrid approach for training recurrent neural networks: application to multi-step-ahead prediction of noisy and large data sets

verfasst von: S. Chtourou, M. Chtourou, O. Hammami

Erschienen in: Neural Computing and Applications | Ausgabe 3/2008

Einloggen

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

search-config

KI-gestützte Suche

Aus

Abstract

Noisy and large data sets are extremely difficult to handle and especially to predict. Time series prediction is a problem, which is frequently addressed by researchers in many engineering fields. This paper presents a hybrid approach to handle a large and noisy data set. In fact, a Self Organizing Map (SOM), combined with multiple recurrent neural networks (RNN) has been trained to predict the components of noisy and large data set. The SOM has been developed to construct incrementally a set of clusters. Each cluster has been represented by a subset of data used to train a recurrent neural network. The back propagation through time has been deployed to train the set of recurrent neural networks. To show the performances of the proposed approach, a problem of instruction addresses prefetching has been treated.

Vorheriger Artikel Enclosing machine learning: concepts and algorithms

Nächster Artikel An improved pulse coupled neural network for image processing

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

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

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+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

Nerrand O, P.Roussel-Ragot, Urbani D, L.Personnaz, Dreyfus G (1994) Training recurrent neural networks: why and how? an illustration in dynamical process modeling. IEEE Trans Neural Netw 5(2):178–184CrossRef

Inoue H, Narihisa H (2000) Predicting chaotic time series by ensembles self-generating neural networks. International joint conference on neural network (IJCNN’00), p 2231

Connor T, Douglas R (1994) Reccurent neural networks and robust time series prediction. IEEE Trans Neural Netw 5(2):240–254CrossRef

Deshpande M, Karipys G (2004) Selective Markov models for predicting web pages accesses. ACM Trans Internet Technol 4(2):163–184CrossRef

Tran N, Reed A (2001) ARIMA time series modeling and forecasting for adaptive I/O prefetching. In: Proceedings of the international conference on supercomputing, pp 473–485

Ho SL, Xie M, Goh TN (2002) A comparative study of neural network and Box–Jenkins ARIMA modeling in time series prediction. In: Proceedings of the 26th international conference on computers and industrial engineering 42(2–4):371–375

Owens AJ (2000) Empirical modeling of very large data sets using neural network. In: Proceedings of the IEEE-INNS-ENNS international joint conference on neural network, vol 6, pp 302–307

Principe JC, Wang L, Motter MA (1998) Local dynamic modelling with self-organizing maps and applications to nonlinear system identification and control. Proc IEEE 86(11)

Cho K, Wang B (1996) Radial basis function based adaptive fuzzy systems and their application to system identification and prediction. Fuzzy Sets Syst 83:325–339CrossRefMathSciNet

10.

Kohonen T (1999) Self-organizing maps and learning vector quantization for feature sequences. Neural Processing Lett 10(2):151–159CrossRef

11.

Leung H, Lo T, Wang S (2001) Prediction of noisy chaotic time series using an optimal radial basis function neural network. IEEE Trans Neural Netw 12(5):1163–1172CrossRef

12.

Lin T, Horn G, Tino P, Lee Giles C (1996) Learning long-term dependencies in NARX recurrent neural networks. IEEE Trans Neural Netw 7(6):1329CrossRef

13.

Lin T, Giles CL, Horne B, Kung SY (1997) A delay damage model selection algorithm for NARX neural networks. IEEE Trans Signal Process 45(11):2719–2730CrossRef

14.

Parlos AG, Rais OT, Atiya AF (2000) Multi-step-ahead prediction using dynamic recurrent neural networks. Neural Netw 13(7):765–786CrossRef

15.

Lee Giles C, Steve Lawrence, Tsoi AC (2001) Noisy time series prediction using a recurrent neural network and grammatical inference. Mach Learning 44(1/2):161–183MATHCrossRef

16.

Motter AM (2000) Predictive multiple model switching control with the self-organizing map. In: Proceedings of international joint conference in neural network, 4(4):IEEE-INNS-ENNS, 4317

17.

Wichard JD, Ogorzalek M (2004) Time series prediction with ensemble models. In: Proceedings of international joint conference in neural network, Busdapest

18.

Chtourou S, Chtourou M, Hammami O (2006) Neural network based memory access prediction support for soc dynamic reconfiguration. In: Proceedings of the international joint conference on neural network, pp 5130–5136

19.

Sherwood T, Sair S, Calder B (2003) Phase tracking and prediction. In: Proceedings of the 30th international symposium on computer architecture (ISCA), pp 336–347

20.

Jimenez DA, Lin C (2002) Neural methods for dynamic branch prediction. ACM Trans Comput Syst 20(4):369–397CrossRef

21.

Sakr MF, Giles CL, Levitan SP, Horne BG, Maggini M, Chiarulli DM (1996) On-line prediction of multiprocessor memory access patterns. In: Proceedings of the IEEE international conference on neural networks, p 1564

22.

Sakr MF, Levitan SP, Chiarulli DM, Horne BG, Giles CL (1997) Predicting multiprocessor memory access patterns with learning models. In: Fisher D (ed) Proceedings of the fourteenth international conference on machine learning. Morgan Kaufmann, San Francisco, pp 305–312

23.

Atiya FA, Parlos AG (2000) New results on recurrent network training: unifying the algorithms and accelerating convergence. IEEE Trans Neural Netw 11(3):697–709CrossRef

24.

Chalup SK, Blair AD (2003) Incremental training of first order recurrent neural networks to predict a context-sensitive language. Neural Netw 16:955–972CrossRef

25.

Liu D, Chang T-S, Zhang Y (2002) A constructive algorithm for feedforward neural networks with incremental training. IEEE Trans Circuits Syst I Fundamental Theory Appl 49(12):1876–1879CrossRef

26.

Dittenbach M, Merkl D, Rauber A (2000) The growing hierarchical self organizing map. In: Proceedings of the international joint conference on neural networks, pp 15–19

27.

Hammond J, MacClean D, Valova I (2006) A parallel implementation of a growing SOM promoting independent neural networks over distributed input space. In: Proceedings of the international joint conference on neural networks, pp 958–965

28.

http://rogue.colorado.edu/Pin/index.html

Titel: A hybrid approach for training recurrent neural networks: application to multi-step-ahead prediction of noisy and large data sets
verfasst von: S. Chtourou
M. Chtourou
O. Hammami
Publikationsdatum: 01.06.2008
Verlag: Springer-Verlag
Erschienen in: Neural Computing and Applications / Ausgabe 3/2008
Print ISSN: 0941-0643
Elektronische ISSN: 1433-3058
DOI: https://doi.org/10.1007/s00521-007-0116-8

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

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

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Springer Professional "Wirtschaft+Technik"

Weitere Artikel der Ausgabe 3/2008

Global exponential stability analysis for cellular neural networks with variable coefficients and delays

Enclosing machine learning: concepts and algorithms

Human face recognition by adaptive processing of tree structures representation

Estimating vigilance level by using EEG and EMG signals

Designing a decompositional rule extraction algorithm for neural networks with bound decomposition tree

Detection and classification of road signs in natural environments