Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

Advertisement

Springer Nature Link
Log in

SARASOM: a supervised architecture based on the recurrent associative SOM

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

We present and evaluate a novel supervised recurrent neural network architecture, the SARASOM, based on the associative self-organizing map. The performance of the SARASOM is evaluated and compared with the Elman network as well as with a hidden Markov model (HMM) in a number of prediction tasks using sequences of letters, including some experiments with a reduced lexicon of 15 words. The results were very encouraging with the SARASOM learning better and performing with better accuracy than both the Elman network and the HMM.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Balkenius C, Morén J, Johansson B, Johnsson M (2010) Ikaros: building cognitive models for robots. Adv Eng Inf 24(1):40–48

    Article  Google Scholar 

  2. Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford

    Google Scholar 

  3. Blunsom P (2004) Hidden markov models. In: Lecture notes, vol 15, pp 18–19

  4. Box GEP, Jenkins GM (1976) Time series analysis: forecasting and control, revised ed. Holden-Day, San Francisco, CA

  5. De Gooijer JG, Hyndman RJ (2006) 25 years of time series forecasting. Int J Forecast 22(3):443–473

    Article  Google Scholar 

  6. Diaz AE, Hernandez CA (2009) Tool for the design and implementation of control systems with neural networks. In: IEEE international conference on intelligent computing and intelligent systems, 2009. ICIS 2009, vol 1

  7. Elman JL (1990) Finding structure in time. Cogn Sci 14:179–211

    Article  Google Scholar 

  8. Elman JL (1991) Distributed representations, simple recurrent networks, and grammatical structure. Mach Learn 7(2):195–225

    Google Scholar 

  9. Erkki AL, Oja E, Simula O (2004) Time series prediction competition: the CATS benchmark. In: The 2004 international joint conference on neural networks (IJCNN), pp 2325–2329

  10. Firat M, Erkan Turan M, Ali Yurdusev M (2010) Comparative analysis of neural network techniques for predicting water consumption time series. J Hydrol 384(1–2):46–51

    Article  Google Scholar 

  11. Gil D, Johnsson M, Garcia Chamizo JM, Soriano A, Ruiz D (2009) Application of artificial neural networks in the diagnosis of urological dysfunctions. Expert Syst Appl 36(3P2):5754–5760

    Article  Google Scholar 

  12. Gil D, Girela JL, De Juan J, Jose Gomez-Torres M, Johnsson M (2012) Predicting seminal quality with artificial intelligence methods. Expert Syst Appl 39(16):12564–12573

    Article  Google Scholar 

  13. Hassan R (2007) PhD thesis: hybrid HMM and soft computing modeling with applications to time series analysis. Computer Science and Software Engineering Department, University of Melbourne, Australia

  14. Hassan R, Nath B (2005) Stockmarket forecasting using hidden Markov model: a new approach. In: IEEE computer society

  15. Johnsson M, Balkenius C (2008) Associating SOM representations of haptic submodalities. In: Proceedings of TAROS 2008, pp 124–129

  16. Johnsson M, Balkenius C (2009) Experiments with self-organizing systems for texture and hardness perception. Glob J Comput Sci Technol 9(4):53–62

    Google Scholar 

  17. Johnsson M, Balkenius C, Hesslow G (2009) Associative self-organizing map. In: International joint conference on computational intelligence (IJCCI) 2009, pp 363–370

  18. Johnsson M, Gil D, Balkenius C, Hesslow G (2010) Supervised architectures for internal simulation of perceptions and actions. In: Proceedings of brain inspired cognitive systems (BICS)

  19. Johnsson M, Gil D, Balkenius C, Hesslow G (2011) Internal simulation in a bimodal system. In: Kofod-Petersen A, Heintz F, Langseth H (eds) Proceedings of the scandinavian conference on artificial intelligence (SCAI) 2011, Trondheim, Norway. IOS Press, pp 173–182, ISBN 978-1-60750-753-6

  20. Johnsson M, Martinsson M, Gil D, Hesslow G (2011) Associative self-organizing map. In: Mwasiagi JI (ed) Self organising maps—applications and novel algorithm design. INTECH, pp 603–626, ISBN: 978-953-307-546-4

  21. Kohonen T (1988) Self-organization and associative memory. Springer, Berlin

    Book  MATH  Google Scholar 

  22. Lemke C, Gabrys B (2010) Meta-learning for time series forecasting in the NN GC1 competition. In: 2010 IEEE international conference on fuzzy systems (FUZZ). IEEE, pp 1–5

  23. Mahamad AK, Hiyama T (2009) Improving Elman network using genetic algorithm for bearing failure diagnosis of induction motor. In: Diagnostics for electric machines, power electronics and drives, 2009. SDEMPED 2009. IEEE international symposium on. IEEE, pp 1–6

  24. Markov A (1971) Extension of the limit theorems of probability theory to a sum of variables connected in a chain. In: Howard R (ed) Dynamic probabilistic systems (vol I: Markov models) chapter Appendix B. Wiley, New York City, pp 552–577

  25. Masterson D, Kushmerick N (2003) Information extraction from multi-document threads. In: ECML-2003: workshop on adaptive text extraction and mining. Citeseer, pp 34–41

  26. MathWorks I (2009) MATLAB & SIMULINK instrument control toolbox. Neural Network Toolbox. The MathWorks Inc.

  27. Moody J, Utans J (1995) Architecture selection strategies for neural networks: application to corporate bond rating prediction. In: Neural networks in the capital markets, pp 277–300

  28. Narasinga Rao MR, Sridhar GR, Madhu K, Rao AA (2010) A clinical decision support system using multi-layer perceptron neural network to predict quality of life in diabetes. Diabetes Metab Syndr Clin Res Rev 4(1):57–59

    Article  Google Scholar 

  29. Rabiner L, Juang B (1986) An introduction to hidden Markov models. ASSP Mag IEEE 3(1):4–16

    Article  Google Scholar 

  30. Rabiner LR (1989) A tutorial on hidden markov models and selected applications in speech recognition. Proc IEEE 77(2):257–286

    Article  Google Scholar 

  31. Rojas I, Valenzuela O, Rojas F, Guillen A, Herrera LJ, Pomares H, Marquez L, Pasadas M (2008) Soft-computing techniques and ARMA model for time series prediction. Neurocomputing 71(4–6):519–537

    Article  Google Scholar 

  32. Temurtas F (2009) A comparative study on thyroid disease diagnosis using neural networks. Expert Syst Appl 36(1):944–949

    Article  Google Scholar 

  33. Wang L, Shi X, Liang Y, Han X (2006) An improved elman neural network with profit factors and its applications. In: Huang D-S, Li K, Irwin GW (eds) Intelligent computing, volume 4113 of lecture notes in computer science. Springer, Berlin, pp 317–322, ISBN 978-3-540-37271-4

  34. Wu CL, Chau KW (2010) Data-driven models for monthly streamflow time series prediction. Eng Appl Artif Intell 23(8):1350–1367

    Article  Google Scholar 

  35. Wyffels F, Schrauwen B (2010) A comparative study of reservoir computing strategies for monthly time series prediction. Neurocomputing 73(10–12):1958–1964

    Article  Google Scholar 

Download references

Acknowledgments

We want to express our acknowledgment to the Ministry of Science and Innovation (Ministerio de Ciencia e Innovación—MICINN) through the “José Castillejo” program from the Government of Spain and to the Swedish Research Council through the Swedish Linnaeus project Cognition, Communication and Learning (CCL) as funders of the work exhibited in this paper. This work was also partially funded by the Spanish Government DPI2013-40534-R.

Author information

Authors and Affiliations

  1. Lucentia Research Group, Computing Technology and Data Processing, University of Alicante, Alicante, Spain

    David Gil

  2. Computing Technology and Data Processing, University of Alicante, Alicante, Spain

    Jose Garcia-Rodriguez

  3. Instituto de Investigación en Informática (IUII), University of Alicante, Alicante, Spain

    Miguel Cazorla

  4. Lund University Cognitive Science, Lund, Sweden

    Magnus Johnsson

Authors
  1. David Gil
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jose Garcia-Rodriguez
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Miguel Cazorla
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Magnus Johnsson
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to David Gil.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gil, D., Garcia-Rodriguez, J., Cazorla, M. et al. SARASOM: a supervised architecture based on the recurrent associative SOM. Neural Comput & Applic 26, 1103–1115 (2015). https://doi.org/10.1007/s00521-014-1785-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-014-1785-8

Keywords

Search

Navigation