Abstract
It is known that dividing an attractor network into a set of subnetworks whose connectivity is equivalent to the attractor network from which they come, and therefore with the same computational cost, increases the system’s recovery capacity. This opens the possibility of optimizing the assignment of pattern subsets to the ensemble modules. The patterns subsets assignment to the network modules can be considered as a combinatorial optimization problem, where varied strategies (i.e. random vs. heuristic assignments) can be tested. In this work, we present a possible heuristic strategy driven by an overlap minimization in the subsets for assigning the patterns input to the modules of the ensemble attractor neural network. In terms of system pattern storage capacity, the assignment driven by the overlap minimization in each subset/module proved to be better than no specific assignment, i.e. distribution of patterns to modules randomly.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Albert, R., Barabási, A.L.: Statistical mechanics of complex networks. Rev. Mod. Phys. 74(1), 47 (2002)
Amit, D.J.: Modeling Brain Function: The World of Attractor Neural Networks. Cambridge University Press, New York (1992)
Arenzon, J., Lemke, N.: Simulating highly diluted neural networks. J. Phys. A Math. Gen. 27(15), 5161 (1994)
Dávila, C., González, M., Pérez-Medina, J.-L., Dominguez, D., Sánchez, Á., Rodriguez, F.B.: Ensemble of attractor networks for 2D gesture retrieval. In: Rojas, I., Joya, G., Catala, A. (eds.) IWANN 2019. LNCS, vol. 11507, pp. 488–499. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20518-8_41
Derrida, B., Gardner, E., Zippelius, A.: An exactly solvable asymmetric neural network model. EPL (Europhys. Lett.) 4(2), 167 (1987)
Dominguez, D., González, M., Rodríguez, F.B., Serrano, E., Erichsen Jr., R., Theumann, W.: Structured information in sparse-code metric neural networks. Phys. A Stat. Mech. Appl. 391(3), 799–808 (2012)
Dominguez, D., González, M., Serrano, E., Rodríguez, F.B.: Structured information in small-world neural networks. Phys. Rev. E 79(2), 021909 (2009)
Doria, F., Erichsen Jr., R., González, M., Rodríguez, F.B., Sánchez, Á., Dominguez, D.: Structured patterns retrieval using a metric attractor network: application to fingerprint recognition. Phys. A Stat. Mech. Appl. 457, 424–436 (2016)
Ghandeharizadeh, S., Irani, S., Lam, J.: The subset assignment problem for data placement in caches. Algorithmica 80(7), 2201–2220 (2018)
González, M., Dávila, C., Dominguez, D., Sánchez, Á., Rodriguez, F.B.: Fingerprint retrieval using a specialized ensemble of attractor networks. In: Rojas, I., Joya, G., Catala, A. (eds.) IWANN 2019. LNCS, vol. 11507, pp. 709–719. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20518-8_59
González, M., Dominguez, D., Sánchez, Á., Rodríguez, F.B.: Capacity and retrieval of a modular set of diluted attractor networks with respect to the global number of neurons. In: Rojas, I., Joya, G., Catala, A. (eds.) IWANN 2017. LNCS, vol. 10305, pp. 497–506. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59153-7_43
Gonzalez, M., Dominguez, D., Sanchez, A., Rodriguez, F.B.: Increase attractor capacity using an ensembled neural network. Expert Syst. Appl. 71, 206–215 (2017). https://doi.org/10.1016/j.eswa.2016.11.035
González, M., Sánchez, Á., Dominguez, D., Rodríguez, F.B.: Ensemble of diluted attractor networks with optimized topology for fingerprint retrieval. Neurocomputing 442, 269–280 (2021)
Hertz, J.A., Krogh, J., Palmer, R.: Introduction to the Theory of Neural Computation. Santa Fe Institute Studies in the Sciences of Complexity, vol. 1. Addison-Wesley (1991)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Nat. Acad. Sci. 79(8), 2554–2558 (1982)
Pentico, D.W.: Assignment problems: a golden anniversary survey. Eur. J. Oper. Res. 176(2), 774–793 (2007)
Staal, J., Abramoff, M., Niemeijer, M., Viergever, M., van Ginneken, B.: Ridge based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging 23(4), 501–509 (2004)
Uhl, A.: State of the art in vascular biometrics. In: Uhl, A., Busch, C., Marcel, S., Veldhuis, R. (eds.) Handbook of Vascular Biometrics. ACVPR, pp. 3–61. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-27731-4_1
Acknowledgments
Funded by UDLA-SIS.MGR.21.04, AEI/FEDER TIN2017-84452-R, PID2020-114867RB-I00, RTI2018-098019-B-I00, and CYTED Network 518RT0559.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
González, M., Sánchez, Á., Dominguez, D., Rodríguez, F.B. (2021). Fine-Tuning of Patterns Assignment to Subnetworks Increases the Capacity of an Attractor Network Ensemble. In: Rojas, I., Joya, G., Català, A. (eds) Advances in Computational Intelligence. IWANN 2021. Lecture Notes in Computer Science(), vol 12862. Springer, Cham. https://doi.org/10.1007/978-3-030-85099-9_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-85099-9_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-85098-2
Online ISBN: 978-3-030-85099-9
eBook Packages: Computer ScienceComputer Science (R0)