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.
Similar content being viewed by others
References
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):178–184
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):240–254
Deshpande M, Karipys G (2004) Selective Markov models for predicting web pages accesses. ACM Trans Internet Technol 4(2):163–184
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 83:325–339
Kohonen T (1999) Self-organizing maps and learning vector quantization for feature sequences. Neural Processing Lett 10(2):151–159
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):1163–1172
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):1329
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):2719–2730
Parlos AG, Rais OT, Atiya AF (2000) Multi-step-ahead prediction using dynamic recurrent neural networks. Neural Netw 13(7):765–786
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):161–183
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
Wichard JD, Ogorzalek M (2004) Time series prediction with ensemble models. In: Proceedings of international joint conference in neural network, Busdapest
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
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
Jimenez DA, Lin C (2002) Neural methods for dynamic branch prediction. ACM Trans Comput Syst 20(4):369–397
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
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
Atiya FA, Parlos AG (2000) New results on recurrent network training: unifying the algorithms and accelerating convergence. IEEE Trans Neural Netw 11(3):697–709
Chalup SK, Blair AD (2003) Incremental training of first order recurrent neural networks to predict a context-sensitive language. Neural Netw 16:955–972
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):1876–1879
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
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
http://rogue.colorado.edu/Pin/index.html
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chtourou, S., Chtourou, M. & Hammami, O. A hybrid approach for training recurrent neural networks: application to multi-step-ahead prediction of noisy and large data sets. Neural Comput & Applic 17, 245–254 (2008). https://doi.org/10.1007/s00521-007-0116-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-007-0116-8