Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

A New Associative Model with Dynamical Synapses

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

The brain is not a huge fixed neural network, but a dynamic, changing neural network that continuously adapts to meet the demands of communication and computational needs. In classical neural networks approaches, particularly associative memory models, synapses are only adjusted during the training phase. After this phase, synapses are no longer adjusted. In this paper we describe a new dynamical model where synapses of the associative memory could be adjusted even after the training phase as a response to an input stimulus. We provide some propositions that guarantee perfect and robust recall of the fundamental set of associations. In addition, we describe the behavior of the proposed associative model under noisy versions of the patterns. At last, we present some experiments aimed to show the accuracy of the proposed model.

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

Similar content being viewed by others

Explore related subjects

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

References

  1. McCulloch WS, Pitts WH (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5: 115–133. doi:10.1007/BF02478259

    Article  MATH  MathSciNet  Google Scholar 

  2. Hebb DO (1949) The organization of behavior. Wiley, New York

    Google Scholar 

  3. Rosenblatt F (1958) The perceptron: a probabilistic model for information storage & organization in the brain. Psychol Rev 65:386–408 Medline. doi:10.1037/h0042519

    Google Scholar 

  4. Rumelhart D, McClelland J (1986) Parallel distributed processing group. MIT Press, London

    Google Scholar 

  5. Steinbuch K (1961) Die Lernmatrix Kybernetik 1(1): 26–45. doi:10.1007/BF00293853

    Google Scholar 

  6. Anderson JA (1972) A simple neural network generating an interactive memory. Math Biosci 14: 197–220. doi:10.1016/0025-5564(72)90075-2

    Article  MATH  Google Scholar 

  7. Kohonen T (1972) Correlation matrix memories. IEEE Trans Comput 21(4): 353–359

    Article  MATH  Google Scholar 

  8. Nakano K (1972) Associatron: a model of associative memory. EEE Trans Syst, Man Cybern SMC- 2(3): 380–388

    Article  Google Scholar 

  9. Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci USA 79: 2554–2558. doi:10.1073/pnas.79.8.2554

    Article  MathSciNet  Google Scholar 

  10. Lu J et al (2006) Topology influences performance in the associative memory neural network. Phys Lett A 354: 335–343. doi:10.1016/j.physleta.2006.01.085

    Article  Google Scholar 

  11. Lee D-L (2006) Improvements of complex-valued Hopfiel associative memory by using generalized projections rules. IEEE Trans Neural Netw 17(5): 1341–1347. doi:10.1109/TNN.2006.878786

    Article  Google Scholar 

  12. Casali D et al (2006) Associative memory design using a support vector machine. IEEE Trans Neural Netw 17(5): 1165–1174. doi:10.1109/TNN.2006.877539

    Article  MathSciNet  Google Scholar 

  13. Tang H et al (2006) Dynamic analysis and analog associative memory of network with LT neurons. IEEE Trans Neural Netw 17(2): 409–418. doi:10.1109/TNN.2005.863457

    Article  Google Scholar 

  14. Charlier S et al (2006) NDRAM : Non linear dynamic recurrent associative memory for learning bipolar and nonbipolar correlated patterns. IEEE Trans Neural Netw 16(6): 1393–1400. doi:10.1109/TNN.2005.852861

    Article  Google Scholar 

  15. Zhu J, von der Malsburg C (2006) Associative memory of conectivety patterns. Neurocomputing 69: 1305–1308. doi:10.1016/j.neucom.2005.12.097

    Article  Google Scholar 

  16. Rehn M, Sommer FT (2006) Storing and restoring visual input with collavorative rank coding and associative memory. Neurocomputing 69: 1219–1223. doi:10.1016/j.neucom.2005.12.080

    Article  Google Scholar 

  17. Mu X et al (2007) A weighted voting model of associative memory. IEEE Trans Neural Netw 18(3): 756–777. doi:10.1109/TNN.2007.891196

    Article  Google Scholar 

  18. Wickramasinghe LK et al (2007) A novel episodic associative memory model for enhanced classification accuracy. Pattern Recognit Lett 28: 1193–1202. doi:10.1016/j.patrec.2007.02.012

    Article  Google Scholar 

  19. Ritter GX, Sussner P, Diazde Leon JL (1998) Morphological associative memories. IEEE Trans Neural Netw 9(2): 281–293. doi:10.1109/72.661123

    Article  Google Scholar 

  20. Chung F-L, Lee T (1996) On fuzzy associative memory with multiple-rule storage capacity. IEEE Trans Fuzzy Syst 4(4): 375–384. doi:10.1109/91.531778

    Article  MathSciNet  Google Scholar 

  21. Wang ST, Lu H (2004) On new fuzzy morphological associative memories. IEEE Trans Fuzzy Syst 12(3): 316–323. doi:10.1109/TFUZZ.2004.825977

    Article  Google Scholar 

  22. Sossa H, Barron R, Vazquez RA (2004) New associative memories to recall real-valued patterns. In: Sanfeliu A, Martínez Trinidad JF, Carrasco-Ochoa JA (eds) Progress in pattern recognition, image analysis and applications, 9th Iberoamerican Congress on Pattern Recognition, CIARP 2004, Puebla, Mexico, October 26–29, 2004, Proceedings. Lecture Notes in Computer Science, N 3287, pp 195–202, Springer

  23. Sussner P, Valle M (2006) Gray-scale morphological associative memories. IEEE Trans Neural Netw 17(3): 559–570. doi:10.1109/TNN.2006.873280

    Article  Google Scholar 

  24. Ehlers MD (2003) Activity level controls postsynaptic composition and signaling via the ubiquitin-proteasome system. Nat Neurosci 6(3): 231–242. doi:10.1038/nn1013

    Article  Google Scholar 

  25. et al (2003) A theory of the thalamocortex Computational models for neuroscience. Springer-Verlag, London, pp 85–124

    Google Scholar 

  26. Arbid MA (2003) The handbook of brain theory and neural networks. The MIT Press, London

    Google Scholar 

  27. Lundqvist M, Rehn M, Lansner A (2006) Attractor dynamics in a modular network model of the cerebral cortex. Neurocomputing 69: 1155–1159. doi:10.1016/j.neucom.2005.12.065

    Article  Google Scholar 

  28. Pantic L et al (2000) Associative memory with dynamic synapses. Neural Comput 14: 2903–2923. doi:10.1162/089976602760805331

    Article  Google Scholar 

  29. Bibitchkov D, Herrman JM, Giesel T (2000) Synaptic depression in associative memory networks. In Proceedings of IJCNN 2000, vol 5, pp 30–35

  30. Wang Z, Fan H (2005) Memory retrieval in a neural network with chaotic neurons and dynamic synapses. In: Cabestany J, Prieto A, Sandoval Hernandez F (eds) IWANN 2005: Computational intelligence and bioinspired systems, 8th International work conference IWANN 2008, Barcelona, Spain, June 8–210, Proceedings. Lecture Notes in Computers Sciences, N 3512, pp 654–660. Springer, New York

  31. Sejnowski TJ (1976) On the stochastic dynamics of neuronal interaction. Biol Cybern 22: 203–211. doi:10.1007/BF00365086

    Article  MATH  Google Scholar 

  32. Makeig S et al (2002) Dynamic brain sources of visual evoked responses. Science 295: 690–694. doi:10.1126/science.1066168

    Article  Google Scholar 

  33. Sossa H, Barron R, Vazquez RA (2007) Study of the influence of the noise in the values of a median associative memory. In: Beliczynski B, Dzielinski A, Iwanowski M, Ribeiro B (eds) Adaptive and natural computing algorithms. 8th International conference, ICANNGA 2007, Warsaw, Poland, April 11–14, 2007, Proceedings, Part II. Lecture Notes in Computer Science, N 4432, pp 55–62, Springer, New York

  34. Laughlin SB, Sejnowski TJ (2003) Communication in neuronal networks. Science 301: 1870–1874. doi:10.1126/science.1089662

    Article  Google Scholar 

  35. Kutas M, Hillyard SA (1984) Brain potentials during reading reflect word expectancy and semantic association. Nature 307: 161–163. doi:10.1038/307161a0

    Article  Google Scholar 

  36. Price CJ (2000) The anatomy of language: contributions from functional neuroimaging. J Anat 197(3): 335–359. doi:10.1046/j.1469-7580.2000.19730335.x

    Article  Google Scholar 

  37. Sossa H, Barron R, Vazquez RA (2004) Transforming fundamental set of patterns to canonical form to improve pattern recall. In: Lemaître Ch, Reyes CA, González JA (eds) Advances in artificial intelligence - IBERAMIA 2004, 9th Ibero-American Conference on AI, Puebla, México, November 22–26, 2004, Proceedings. Lecture Notes in Artificial Intelligence, N 3315, pp 687–696, Springer

  38. Reinvan I (1998) Amnestic disorders and their role in cognitive theory. Scand J Psychol 39(3): 141–143. doi:10.1111/1467-9450.393068

    Article  Google Scholar 

  39. Jovanova-Nesic KD, Jankovic BD (2005) The neuronal and immune memory systems as supervisors of neural plasticity and aging of the brain: from phenomenology to coding of information. Ann N Y Acad Sci 1057: 279–295. doi:10.1196/annals.1356.022

    Article  Google Scholar 

  40. Nene SA et al (1996) Columbia Object Image Library (COIL 100). Technical Report No. CUCS-006-96. Department of Computer Science, Columbia University

  41. Vazquez RA, Sossa H (2006) Image categorization using associative memories. In: Martínez Trinidad JF, Carrasco-Ochoa JA, Kittler J (eds) Progress in pattern recognition, image analysis and applications, 11th Iberoamerican Congress in Pattern Recognition, CIARP 2006, Cancun, Mexico, November 14–17, 2006, Proceedings. Lecture Notes in Computer Science, N 4225, pp 549–558. Springer, New York

  42. Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans SMC 9(1): 62–66

    MathSciNet  Google Scholar 

  43. Hu MK (1962) Visual pattern recognition by moment invariants. IRE Trans Inf Theory 8: 179–187

    Google Scholar 

  44. Gonzalez RC, Woods RE (2002) Digital image processing. 2nd edn. Prentice Hall

  45. Vazquez RA, Sossa H, Garro BA (2007) 3D Object recognition based on low frequencies response and random feature selections. In: MICAI 2007: Advances in Artificial Intelligence, 6th Mexican International Conference on Artificial Intelligence, Aguascalientes, Mexico, November 5–9, 2007, Proceedings. Lecture Notes in Artificial Intelligence, N 4827, pp 694–704, Springer, New York

  46. Vazquez RA, Sossa H, Garro BA (2007) Face recognition using some aspects of the infant vision system and associative memories. In: Rueda L, Mery D, Kittler J (eds) Progress in Pattern Recognition, Image Analysis and Applications, 12th Iberoamerican Congress in Pattern Recognition, CIARP 2007, Valparaiso, Chile, November 13–16, 2007, Proceedings. Lecture Notes in Computer Science, N 4756, pp 437–446, Springer, New York

  47. Vazquez RA, Sossa H, Garro BA (2007). Low frequency responses and random feature selection applied to face recognition. In: Kamel M, Campilho A (eds) ICIAR 2007: Image Analysis and Recognition, International conference ICIAR 2007, Toronto, Canada, August 22–24, Proceedings. Lecture Notes in Computers Sciences, N 4633, pp 818–830, Springer, New York

  48. Vazquez RA, Sossa H (2008) Voice translator based on associative memories. In: Sun F, Zhang J, Tan Y, Cao J, Yu W (eds) Advances in neural networks. ISNN 2008, Beijing, China, September 24–128, 2008, Proceedings. Lecture Notes in Computer Science, N 5264, Part II, pp 341–350, 830, Springer, New York

  49. Vazquez RA, Sossa H (2008) Associative memories applied to pattern recognition. In: Kurkova V, Neruda R, Koutnik J (eds) Artificial neural networks. ICANN 2008, Prague, Czech Republic, September 3–19, 2008, Proceedings. Lecture Notes in Computer Science, N 5164, Part II, pp 111–120, Springer, New York

Download references

Author information

Authors and Affiliations

  1. Centro de Investigación en Computación – IPN, Av. Juan de Dios Bátiz s/n, Esquina con Miguel Othón de Mendizábal, Colonia Nueva Industrial Vallejo, C. P. 07700, México DF, Mexico

    Roberto A. Vázquez Espinoza de los Monteros & Juan Humberto Sossa Azuela

Authors
  1. Roberto A. Vázquez Espinoza de los Monteros
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Juan Humberto Sossa Azuela
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Roberto A. Vázquez Espinoza de los Monteros.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Vázquez Espinoza de los Monteros, R.A., Sossa Azuela, J.H. A New Associative Model with Dynamical Synapses. Neural Process Lett 28, 189–207 (2008). https://doi.org/10.1007/s11063-008-9089-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-008-9089-6

Keywords

Search

Navigation