Skip to main content
SpringerLink
Log in

Associative Memory Networks with Multidimensional Neurons

  • Conference paper
  • First Online:
Artificial Neural Networks and Machine Learning – ICANN 2022 (ICANN 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13529))

Included in the following conference series:

  • 2215 Accesses

Abstract

Neural networks normally used to model associative memory can be regarded as consisting of dissipative units (the neurons) that interact in such a way that the network itself admits a global energy or Liapunov function. The network’s global dynamics is such that the system always evolves “downhill” in the energy landscape. In most models for associative memory, the individual neurons are described as one-dimensional, dynamical systems. In the present contribution, we explore the possibility of extending the structural scheme of associative memory neural networks to more general scenarios, where the units (that is, the neurons) are modeled as multi-dimensional, dissipative systems. With that aim in mind, we advance a coupling scheme for dissipative, multi-dimensional units, that generates dynamical features akin to those required when modeling associative memory.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Aggarwal, C.C.: Neural Networks and Deep Learning. Springer, Cham, Switzerland (2018)

    Book  MATH  Google Scholar 

  2. Barbosa, V.C.: Massively Parallel Models of Computation: Distributed Parallel Processing in Artificial Intelligence and Optimisation. Ellis Horwood, River (1993)

    MATH  Google Scholar 

  3. Berto, F., Tagliabue, J., Rossi, G.: There’s plenty of Boole at the bottom: a reversible CA against information entropy. Mind. Mach. 26(4), 341–357 (2016). https://doi.org/10.1007/s11023-016-9401-6

    Article  Google Scholar 

  4. Cabessa, J., Villa, A.E.P.: Attractor dynamics of a Boolean model of a brain circuit controlled by multiple parameters. Chaos: Interdisc. J. Nonlinear Sci. 28(10), 106318 (2018)

    Google Scholar 

  5. Carhart-Harris, R.L., Friston, K.J.: Free-energy and Freud: an update. In: Fotopoulou, A., Pfaff, D., Conway, M.A. (eds.) From the couch to the lab: Trends in psychodynamic neuroscience, pp. 219–229. Oxford Univ. Press, Oxford (2012)

    Chapter  Google Scholar 

  6. Cleeremans, A., Timmermans, B., Pasquali, A.: Consciousness and metarepresentation: a computational sketch. Neural Netw. 20, 1032–1039 (2007)

    Article  Google Scholar 

  7. Cohen, M.A., Grossberg, S.: Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans. Syst. Man Cybern. 13, 815–826 (1983)

    Article  MathSciNet  MATH  Google Scholar 

  8. Cranford, J.L.: Astrobiological Neurosystems: Rise and Fall of Intelligent Life Forms in the Universe. Springer, Cham (2015)

    Book  Google Scholar 

  9. De Wilde, P.: Class of Hamiltonian neural networks. Phys. Rev. E 47(2), 1392–1396 (1993)

    Article  MathSciNet  Google Scholar 

  10. Edalat, A., Mancinelli, F.: Strong attractors of Hopfield neural networks to model attachment types and behavioural patterns. In: Angelov, P., Levine, D., Apolloni, B. (eds.) Proceedings of the 2013 International Joint Conference on Neural Networks (IJCNN), Red Hook, NY, pp. 14027190-1–10. IEEE (2013)

    Google Scholar 

  11. Fagerholm, E.D., Foulkes, W.M.C., Friston, K.J., Moran, R.J., Leech, R.: Rendering neuronal state equations compatible with the principle of stationary action. J. Math. Neurosci. 11(1), 1–15 (2021). https://doi.org/10.1186/s13408-021-00108-0

    Article  MathSciNet  MATH  Google Scholar 

  12. Hertz, J.A., Krogh, A., Palmer, R.G.: Introduction to the Theory of Neural Computation. Lecture Notes, vol. 1. Perseus Books, Cambridge, MA, USA (1991)

    Google Scholar 

  13. Hopfield, J.J.: Neurons with graded responses have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. 81, 3088–3092 (1984)

    Article  MATH  Google Scholar 

  14. Kandel, E.: Psychiatry, Psychoanalysis, and the New Biology of Mind. American Psychiatric Publishing Inc, Washington D.C. (2005)

    Google Scholar 

  15. Kerner, E.H.: A statistical mechanics of interacting biological species. Bull. Math. Biophys. 19, 121–146 (1957). https://doi.org/10.1007/BF02477883

    Article  MathSciNet  Google Scholar 

  16. Kerner, E.H.: Note on Hamiltonian format of Lotka-Volterra dynamics. Phys. Lett. A 151(8), 401–402 (1990)

    Article  MathSciNet  Google Scholar 

  17. Knoblauch, A., Palm, G.: Iterative retrieval and block coding in autoassociative and heteroassociative memory. Neural Comput. 32(1), 205–260 (2020)

    Article  MathSciNet  MATH  Google Scholar 

  18. Lotka, A.J.: Elements of Mathematical Biology. Dover, New York (1956)

    MATH  Google Scholar 

  19. de Luca, V.T.F., Wedemann, R.S., Plastino, A.R.: Neuronal asymmetries and Fokker-Planck dynamics. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11141, pp. 703–713. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01424-7_69

    Chapter  Google Scholar 

  20. McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5(4), 115–133 (1943). https://doi.org/10.1007/BF02478259

    Article  MathSciNet  MATH  Google Scholar 

  21. Nowak, M.A.: Evolutionary Dynamics. Harvard University Press, Cambridge (2006)

    Book  MATH  Google Scholar 

  22. Palm, G.: Neural Assemblies, An Alternative Approach to Artificial Intelligence. Studies of Brain Function, Springer-Verlag, Berlin, Heidelberg (1982)

    Google Scholar 

  23. Plastino, A.R., Anteneodo, C.: A dynamical thermostatting approach to nonextensive canonical ensembles. Ann. Phys. 255(2), 250–269 (1997)

    Article  MathSciNet  MATH  Google Scholar 

  24. Salakhutdinov, R.R., Hinton, G.E.: Replicated softmax: an undirected topic model. In: Bengio, Y., Schuurmans, D., Lafferty, J., Williams, C., Culotta, A. (eds.) Advances in Neural Information Processing Systems (NIPS 2009), vol. 22. Curran Associates, Inc. (2009)

    Google Scholar 

  25. Siddiqui, M., Wedemann, R.S., Jensen, H.J.: Avalanches and generalized memory associativity in a network model for conscious and unconscious mental functioning. Phys. A 490, 127–138 (2018)

    Article  MathSciNet  MATH  Google Scholar 

  26. Srivastava, N., Salakhutdinov, R.R., Hinton, G.: Modeling documents with deep Boltzmann machines. In: Nicholson, A., Smyth, P. (eds.) Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI2013), pp. 616–624. UAI 2013, AUAI Press, Arlington, Virginia, USA (2013)

    Google Scholar 

  27. Stewart, I., Golubitsky, M.: Symmetric networks with geometric constraints as models of visual illusions. Symmetry 11(6), 799 (2019)

    Article  Google Scholar 

  28. Taylor, J.G., Villa, A.E.P.: The “Conscious I”: a neuroheuristic approach to the mind. In: Baltimore, D., Dulbecco, R., Francois, J., Levi-Montalcini, R. (eds.) Frontiers of Life, vol. 3, pp. 349–368. Academic Press (2001)

    Google Scholar 

  29. Taylor, J.G.: A neural model of the loss of self in schizophrenia. Schizophrenia Bull. 37(6), 1229–1247 (2011)

    Article  Google Scholar 

  30. Torres, J.J., Manzano, D.: A model of interacting quantum neurons with a dynamic synapse. New J. Phys. 24, 073007 (2022)

    Google Scholar 

  31. Tsallis, C., Stariolo, D.A.: Generalized simulated annealing. Phys. A 233, 395–406 (1996)

    Article  Google Scholar 

  32. Vanchurin, V.: The world as a neural network. Entropy 22(11), 1210 (2020)

    Article  MathSciNet  Google Scholar 

  33. Wedemann, R.S., Donangelo, R., de Carvalho, L.A.V.: Generalized memory associativity in a network model for the neuroses. Chaos 19(1), 015116-(1–11) (2009)

    Google Scholar 

  34. Wedemann, R.S., Plastino, A.R.: \(q\)-Maximum entropy distributions and memory neural networks. In: Lintas, A., Rovetta, S., Verschure, P.F.M.J., Villa, A.E.P. (eds.) Artificial Neural Networks and Machine Learning - ICANN 2017. LNCS, vol. 10613, pp. 300–308. Springer, Cham (2017)

    Chapter  Google Scholar 

  35. Wedemann, R.S., Plastino, A.R.: A nonlinear Fokker-Planck description of continuous neural network dynamics. In: Tetko, I.V., Kurková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11727, pp. 43–56. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30487-4_4

    Chapter  Google Scholar 

  36. Wedemann, R.S., Plastino, A.R.: Nonlinear Lagrangean neural networks. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds.) ICANN 2021. LNCS, vol. 12894, pp. 163–173. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86380-7_14

    Chapter  Google Scholar 

  37. Wedemann, R.S., Plastino, A.R., Tsallis, C.: Curl forces and the nonlinear Fokker-Planck equation. Phys. Rev. E 94(6), 062105 (2016)

    Google Scholar 

  38. Wedemann, R.S., de Carvalho, L.A.V., Donangelo, R.: Complex Networks in Psychological Models. Prog. Theor. Phys. Suppl. 162, 121–130 (2006)

    Google Scholar 

  39. Wedemann, R.S., de Carvalho, L.A.V., Donangelo, R.: Network properties of a model for conscious and unconscious mental processes. Neurocomputing 71(16), 3367–3371 (2008)

    Article  Google Scholar 

  40. Wedemann, R.S., Plastino, A.R.: Nonlinear, nonequilibrium landscape approach to neural network dynamics. In: Farkaš, I., Masulli, P., Wermter, S. (eds.) ICANN 2020. LNCS, vol. 12397, pp. 180–191. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61616-8_15

    Chapter  Google Scholar 

  41. Wedemann, R.S., Plastino, A.R.: Nonlinear Fokker-Planck approach to the Cohen-Grossberg model. In: Lintas, A., Enrico, P., Pan, X., Wang, R., Villa, A. (eds.) Advances in Cognitive Neurodynamics (VII), pp. 61–72. Springer, Singapore (2021)

    Chapter  Google Scholar 

Download references

Acknowledgments

We acknowledge financial support from the Brazilian funding agencies: Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq), Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro (FAPERJ) and Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES). The authors are also grateful for the kind hospitality of the Centro Brasileiro de Pesquisas Físicas (CBPF), where part of this research was conducted.

Author information

Authors and Affiliations

  1. Instituto de Matemática e Estatística, Universidade do Estado do Rio de Janeiro, Rua São Francisco Xavier 524, Rio de Janeiro, RJ, 20550-900, Brazil

    Roseli S. Wedemann

  2. CeBio y Departamento de Ciencias Básicas, Universidad Nacional del Noroeste de la Provincia de Buenos Aires, UNNOBA, Conicet, Roque Saenz Peña 456, Junin, Argentina

    Angel R. Plastino

  3. Centro Brasileiro de Pesquisas Físicas (CBPF), Rua Xavier Sigaud 150, Rio de Janeiro, RJ, 22290-180, Brazil

    Angel R. Plastino

Authors
  1. Roseli S. Wedemann
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Angel R. Plastino
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Roseli S. Wedemann .

Editor information

Editors and Affiliations

  1. University of the West of England, Bristol, UK

    Elias Pimenidis

  2. Lancaster University, Lancaster, UK

    Plamen Angelov

  3. Digital Innovation, Teesside University, Middlesbrough, UK

    Chrisina Jayne

  4. Democritus University of Thrace, Xanthi, Greece

    Antonios Papaleonidas

  5. The University of the West of England, Bristol, UK

    Mehmet Aydin

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wedemann, R.S., Plastino, A.R. (2022). Associative Memory Networks with Multidimensional Neurons. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol 13529. Springer, Cham. https://doi.org/10.1007/978-3-031-15919-0_42

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-15919-0_42

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-15918-3

  • Online ISBN: 978-3-031-15919-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation