Advertisement

Spin-glass Implementation of a Hopfield Neural Structure

  • Łukasz Laskowski
  • Magdalena Laskowska
  • Jerzy Jelonkiewicz
  • Arnaud Boullanger
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8467)

Abstract

Paper presents the hardware implementation of the Hopfield continuous neural network. We propose a molecular realization of a spin glass model. In particular, we consider a spin glass like structure that allows interconnection strengths change and neuron state test. Proposed device is based on SBA-15 mesoporous silica thin film, activated by Mn 12 molecular magnets. Our idea seems to be feasible from the technological point of view.

Keywords

Hopfield neural network artificial neuron spin-glass 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bartczuk, Ł., Przybył, A., Dziwiński, P.: Hybrid state variables - fuzzy logic modelling of nonlinear objects. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013, Part I. LNCS, vol. 7894, pp. 227–234. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  2. 2.
    Sherer, R.: Neuro-Fuzzy Relational Systems for Nonlinear Approximation and Prediction. Nonlinear Analysis 71, 1420–1425 (2009)CrossRefGoogle Scholar
  3. 3.
    Cierniak, R.: A new approach to image reconstruction from projections problem using a recurrent neural network. Applied Mathematics and Computer Science 18, 147–157 (2008)MathSciNetGoogle Scholar
  4. 4.
    Cierniak, R.: New neural network algorithm for image reconstruction from fan-beam projections. Neurocomputing 72, 3238–3244 (2009)CrossRefGoogle Scholar
  5. 5.
    McCartor, H.: A Highly Parallel Digital Architecture for Neural Network Emulation. In: VLSI for Artificial Intelligence and Neural Networks, pp. 357–366 (1991)Google Scholar
  6. 6.
    Ramacher, U., Raab, W., Anlauf, J., Hachmann, U., Beichter, J., Bruls, N., Webeling, M., Sicheneder, E.: Multiprocessor and Memory Architecture of the Neurocomputers SYNAPSE-1. In: Proceedings of the 3rd International Conference on Microelectronics for Neural Networks (Micro Neuro), pp. 227–231 (1993)Google Scholar
  7. 7.
    Jahnke, A., Roth, U., Klar, H.: A SIMD/Dataflow Architecture for a Neurocomputer for Spike-Processing Neural Networks (NESPINN). In: Proceedings of the 6th International Conference on Microelectronics for Neural Networks (Micro Neuro), pp. 232–237 (1996)Google Scholar
  8. 8.
    Schwartz, T.J.: A Neural Chips Survey. AI Expert 5(12), 34–39 (1990)Google Scholar
  9. 9.
    Tam, S., Gupta, B., Castro, H., Holler, M.: Learning on an Analog VLSI Neural Network Chip. In: Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (1990)Google Scholar
  10. 10.
    Rutkowski, L., Cpalka, K.: Neuro-fuzzy systems derived from quasi-triangular norms. In: Proceedings of the IEEE International Conference on Fuzzy Systems, vol. 2, pp. 1031–1036 (2004)Google Scholar
  11. 11.
    Fischer, K.H., Hertz, J.A.: Spin Glasses. Cambridge University Press (1991)Google Scholar
  12. 12.
    Prampero, P., Attux, R.: Magnetic particle swarm optimization. Journal of Artificial Intelligence and Soft Computing Research 2(1), 59–72 (2012)Google Scholar
  13. 13.
    Binder, K., Young, A.P.: Spin glasses: Experimental facts, theoretical concepts, and open questions. Review of Modern Physics 58, 801–976 (1986)CrossRefGoogle Scholar
  14. 14.
    Palmer, R.G.: Broken ergodicity in spin-glasses. Lecture Notes in Physics, vol. 192, pp. 234–251 (1983)Google Scholar
  15. 15.
    Hopfield, J.J., Tank, D.W.: “Neural” computation of decisions in optimization problems. Biological Cybernetics 52, 141–152 (1985)zbMATHMathSciNetGoogle Scholar
  16. 16.
    Hopfield, J.J., Tank, D.W.: Artificial neural networks. IEEE Circuits and Devices Magazine 8, 3–10 (1988)CrossRefGoogle Scholar
  17. 17.
    Kataoka, S., Endo, A., Harada, A., Ohmori, T.: Fabrication of mesoporous silica thin films inside microreactors. Materials Letters 62, 723–726 (2008)CrossRefGoogle Scholar
  18. 18.
    Naitabdi, A., Bucher, J.P., Gerbier, P., Rabu, P., Drillon, M.: Self-assembly and magnetism of Mn12 nanomagnets on native and functionalized gold surfaces. Adv. Materials 17, 1612–1616 (2005)CrossRefGoogle Scholar
  19. 19.
    Laskowski, L., Kassiba, A., Makowska-Janusik, M., Mehdi, A., Gibaud, A., Errien, N., Swiatek, J.: Magnetic behaviour of nickel-cyclam complexes in mesoporous silica: EPR investigations. J. Phys.: Condens. Matter 21, 076004 (2009)Google Scholar
  20. 20.
    Laskowska, M., Laskowski, L., Dzilinski, K.: Mesoporous silica functionalized by Nickel-cyclam molecules: preparation and Raman investigations. Current Topics in Biophysics 35, 11–18 (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Łukasz Laskowski
    • 1
    • 2
  • Magdalena Laskowska
    • 2
  • Jerzy Jelonkiewicz
    • 1
  • Arnaud Boullanger
    • 3
  1. 1.Department of Computer EngineeringCzestochowa University of TechnologyCzestochowaPoland
  2. 2.Institute of PhysicsCzestochowa University of TechnologyCzestochowaPoland
  3. 3.Chimie Moléculaire et Organisation du Solide, Institut Charles GerhardtUniversité Montpellier IIMontpellier Cedex 5France

Personalised recommendations