Skip to main content
SpringerLink
Log in

A brain-inspired fuzzy semantic memory model for learning and reasoning with uncertainty

  • ICONIP2006
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Decision-making pervades the human experience. The human decision process is driven by rational reasoning, which is the capacity to use the faculty of reason to facilitate logical thinking and to derive uncertain but sensible arguments from existing knowledge and the observed fact. Knowledge refers to the accumulation and the continuous neurological organization of information via the repeated exposure to its effective usage. Functionally, a decision support system seeks to provide a systematic and human-like way to data analysis by synthesizing an expert’s knowledge and reasoning capability to support the decision process of the user. However, conventional knowledge engineering and decision support systems often performed poorly when they are applied to problem domains festered with uncertain information, where the quality of the observed data is compromised by measurement noises. This paper presents T2-GenSoFNN, a brain-inspired fuzzy semantic memory model embedded with Type-2 fuzzy logic inference for learning and reasoning with noise-corrupted data. The proposed T2-GenSoFNN model is applied to the modeling of human insulin levels for the proper regulation of blood glucose concentration in diabetes therapy. The results are encouraging.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

References

  1. Wilson RA, Keils FC (2001) The MIT encyclopedia of the cognitive sciences. MIT Press, Cambridge

  2. Tomporowski PD (2003) The psychology of skill: a life-span approach. Praeger, New York

  3. Sweatt JD (2003) Mechanisms of memory. Elsevier, Amsterdam

  4. Smith JD, Washburn DA (2005) Uncertainty monitoring and metacognition by animals. Curr Dir Psychol Sci 14:19–24

    Article  Google Scholar 

  5. Ballard DH (1997) An introduction to natural computation. MIT, Cambridge

  6. Buntine W (1992) Learning classification trees. Stat Comput 2:63–73

    Article  Google Scholar 

  7. Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other Kernel-based learning methods. Cambridge University Press, Cambridge

  8. Berenji HR, Khedkar P (1992) Learning and tuning fuzzy logic controllers through reinforcements. IEEE Trans Neural Netw 3:724–740

    Article  Google Scholar 

  9. Karnik NN, Mendel JM, Liang Q (1999) Type-2 fuzzy logic systems. IEEE Trans Fuzzy Syst 7:643–658

    Article  Google Scholar 

  10. Tung WL, Quek C (2002) GenSoFNN: a generic self-organizing fuzzy neural network. IEEE Trans Neural Netw 13:1075–1086

    Article  Google Scholar 

  11. Kandel ER, Schwartz JH, Jessell TM (2000) Principles of neural science, 4th edn. McGraw-Hill, Health Professions Division, New York

  12. Mamdani EH (1977) Application of fuzzy logic to approximate reasoning using linguistic systems. IEEE Trans Comput C-26:1182–1191

    Article  Google Scholar 

  13. Quartz S, Sejnowski TJ (1997) The neural basis of cognitive development: a constructivist manifesto. Behav Brain Sci 20:537–596

    Article  Google Scholar 

  14. Ratcliff R (1990) Connectionist models of recognition memory: constraints imposed by learning and forgetting functions. Psychol Rev 96:523–568

    Google Scholar 

  15. Kandel ER, Kupfermann I, Iversen S (2000) Learning and Memory. In: Kandel ER, Schwartz JH, Jessell TM (eds) Principles of neural science, 4th edn. McGraw-Hill, New York, pp 1227–1246

  16. Amaral DG, Petersen S (1999) Functional imaging of the human hippocampus. A special issue of Hippocampus, 9(1)

  17. Damasio AR, Damasio H, Christen Y (1996) Neurobiology of decision-making. Springer, Heidelberg

    Google Scholar 

  18. Henke K, Buck A, Weber B, Wieser HG (1997) Human hippocampus establishes associations in memory. Hippocampus 7:249–256

    Article  Google Scholar 

  19. McCloskey M, Cohen NJ (1989) Catastrophic interference in connectionist networks: the sequential learning problem. In: Bower GH (ed) The psychology of learning and motivation, vol 24. Academic, New York

  20. Kempermann G, Wiskott L, Gage FH (2004) Functional significance of adult neurogenesis. Curr Opin Neurobiol 14:186–191

    Article  Google Scholar 

  21. Wiskott L, Rasch M, Kempermann G (2006) A functional hypothesis for adult hippocampal neurogenesis: avoidance of catastrophic interference in the dentate gyrus. Hippocampus 16(3):329–343

    Article  Google Scholar 

  22. Tung WL (2004) A generalized framework for fuzzy neural architecture. Doctoral Thesis, School of Computer Engineering, Nanyang Technological University, Singapore

  23. Casillas J, Cordon O, Herrera F, Magdalena L (2003) Interpretability improvements to find the balance interpretability–accuracy in fuzzy modeling: an overview. In: Casillas J, Cordon O, Herrera F, Magdalena L (eds) Interpretability issues in fuzzy modeling. Springer, Heidelberg

  24. Marin JG-Blazquez, Shen Q (2002) From approximative to descriptive fuzzy classifiers. IEEE Trans Fuzzy Syst 10:484–497

    Article  Google Scholar 

  25. Toth H (1997) Fuzziness: from epistemic considerations to terminological clarification. Int J Uncertain Fuzz Knowl Based Syst 5:481–503

    Article  Google Scholar 

  26. Liang Q, Mendel JM (2000) Interval Type-2 fuzzy logic systems: theory and design. IEEE Trans Fuzzy Syst 8:535–550

    Article  Google Scholar 

  27. Tung WL, Quek C (2002) DIC: a novel discrete incremental clustering technique for the derivation of fuzzy membership functions. In: Lecture notes in artificial intelligence 2417—PRICAI 2002: trends in artificial intelligence, pp 178–187

  28. Tung WL, Quek C (2005) GenSo-FDSS: a neural-fuzzy decision support system for pediatric ALL cancer subtype identification using gene expression data. Artif Intell Med 33:61–88

    Article  Google Scholar 

  29. Postman L, Jenkins WO, Postman DL (1948) An experimental comparison of active recall and recognition. Am J Psychol 61:511–519

    Article  Google Scholar 

  30. Schacter DL (1996) Searching for memory: the brain, the mind and the past. Basic Books, New York

  31. DirecNet (2004) Accuracy of the glucowatch G2 biographer and the continuous glucose monitoring system during hypoglycemia. Diabetes Care 27:722–726

    Article  Google Scholar 

  32. Tung WL, Teddy SD, Zhao G (2005) Neurologically inspired modeling of the human glucose metabolic process. Centre for Computational Intelligence, School of Computer Engineering, Nanyang Technological University, C2i-TR-05/002

  33. GlucoSim, Online. http://www.216.47.139.196/glucosim/index.html

  34. Jang JSR (1993) ANFIS: Adaptive-network-based fuzzy inference systems. IEEE Trans Syst Man Cyberns 23:665–685

    Article  Google Scholar 

  35. Tung WL, Quek C, Cheng PYK (2004) GenSo-EWS: a novel neural-fuzzy based early warning system for predicting bank failures. Neural Netw 17:567–587

    Article  Google Scholar 

  36. Sietsma J, Dow RJF (1991) Creating artificial neural networks that generalize. Neural Netw 4:67–79

    Article  Google Scholar 

  37. Webb AR (1994) Functional approximation by feed-forward networks: a least-squares approach to generalization. IEEE Trans Neural Netw 5:363–371

    Article  Google Scholar 

  38. Bishop CM (1995) Training with noise is equivalent to Tikhonov regularization. Neural Comput 7:108–116

    Google Scholar 

  39. Centre for Computational Intelligence, Online. http://www.c2i.ntu.edu.sg

  40. Ang KK, Quek C (2005) RSPOP: rough set-based pseudo outer-product fuzzy rule identification algorithm. Neural Comput 17:205–243

    Article  MATH  Google Scholar 

  41. Quah KH, Quek C (2006) FITSK: online local learning with generic fuzzy input Takagi–Sugeno–Kang fuzzy framework for nonlinear system estimation. IEEE Trans Syst Man Cybern Part B 36:166–178

    Article  Google Scholar 

  42. Tung WL, Quek C (2004) Falcon: neural fuzzy control and decision systems using FKP and PFKP clustering algorithms. IEEE Trans Syst Man Cybern Part B 34:686–695

    Article  Google Scholar 

  43. Quek C, Tung WL (2001) A novel approach to the derivation of fuzzy membership functions using the Falcon-MART architecture. Pattern Recognit Lett 22:941–958

    Article  MATH  Google Scholar 

  44. Ang KK, Quek C, Pasquier M (2003) POPFNN-CRI(S): pseudo outer product based fuzzy neural network using the compositional rule of inference and singleton fuzzifier. IEEE Trans Syst Man Cybern Part B 33:838–849

    Article  Google Scholar 

  45. Quek C, Zhou RW (1996) POPFNN: a pseudo outer-product based fuzzy neural network. Neural Netw 9:1569–1581

    Article  MATH  Google Scholar 

  46. Quah KH, Quek C (2006) Maximum reward reinforcement learning: a non-cumulative reward criterion. Expert Syst Appl 31:351–359

    Article  Google Scholar 

  47. Sim JEW, Tung WL, Quek C (2006) FCMAC-Yager: A novel yager inference scheme based fuzzy CMAC. IEEE Trans Neural Netw 17(6):1394–1410

    Article  Google Scholar 

  48. Teddy SD, Lai EMK, Quek C (2006) Hierarchically clustered adaptive quantization CMAC and its learning convergence. IEEE Trans Neural Netw (in press)

  49. Pasquier M, Quek C, Toh M (2001) Fuzzylot: a novel self-organizing fuzzy-neural rule-based pilot system for automated vehicles. Neural Netw 14:1099–1112

    Article  Google Scholar 

  50. Quek C, Zhou RW (2002) Antiforgery: a novel pseudo-outer product based fuzzy neural network driven signature verification system. Pattern Recognit Lett 23:1795–1816

    Article  MATH  Google Scholar 

  51. Ang KK, Quek C, Wahab A (2001) MCMAC-CVT: a novel on-line associative memory based CVT transmission control system. Neural Netw 15:219–236

    Article  Google Scholar 

  52. Quek C, Tan B, Sagar V (2001) POPFNN-based fingerprint verification system. Neural Netw 14:305–323

    Article  Google Scholar 

  53. Tan TZ, Quek C, Ng GS (2005) Ovarian cancer diagnosis by hippocampus and neocortex-inspired learning memory structure. Neural Netw 18:818–825

    Article  Google Scholar 

  54. Ang KK, Quek C (2006) Stock trading using RSPOP: a novel rough set-based neuro-fuzzy approach. IEEE Trans Neural Netw 17(5):1301–1315

    Article  Google Scholar 

Download references

Acknowledgments

The work of W. L. Tung was supported by a postdoctoral research fellowship from the Singapore Millennium Foundation (SMF- http://www.smf-scholar.org/).

Author information

Authors and Affiliations

  1. Center for Computational Intelligence, Block N4 #2A-32, School of Computer Engineering, Nanyang Technological University, Nanyang Avenue, Singapore, Singapore, 639798

    W. L. Tung & C. Quek

Authors
  1. W. L. Tung
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. C. Quek
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to C. Quek.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Tung, W.L., Quek, C. A brain-inspired fuzzy semantic memory model for learning and reasoning with uncertainty. Neural Comput & Applic 16, 559–569 (2007). https://doi.org/10.1007/s00521-007-0101-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-007-0101-2

Keywords

Search

Navigation