Abstract
The modularity and hierarchical structures in associative networks can replicate parallel pattern retrieval and multitasking abilities found in complex neural systems. These properties can be exhibited in an ensemble of diluted Attractor Neural Networks for pattern retrieval. It has been shown in a previous work that this modular structure increases the single attractor storage capacity using a divide-and-conquer approach of subnetwork diluted modules. Each diluted module in the ensemble learns disjoint subsets of unbiased binary patterns. The present article deals with an ensemble of diluted Attractor Neural Networks which is studied for different values of the global number of network units, and their performance is compared with a single fully connected network keeping the same cost (total number of connections). The ensemble system more than doubles the maximal capacity of the single network with the same wiring cost. The presented approach can be useful for engineering applications to limited memory systems such as embedded systems or smartphones.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Agliari, E., Barra, A., Galluzzi, A., Guerra, F., Moauro, F.: Multitasking associative networks. Phys. Rev. Lett. 109(26), 268101 (2012)
Agliari, E., Barra, A., Galluzzi, A., Guerra, F., Tantari, D., Tavani, F.: Hierarchical neural networks perform both serial and parallel processing. Neural Netw. 66, 22–35 (2015)
Agliari, E., Barra, A., Galluzzi, A., Guerra, F., Tantari, D., Tavani, F.: Metastable states in the hierarchical Dyson model drive parallel processing in the hierarchical Hopfield network. J. Phys. A: Math. Theoret. 48(1), 015001 (2015). http://stacks.iop.org/1751-8121/48/i=1/a=015001
Agliari, E., Barra, A., Galluzzi, A., Guerra, F., Tantari, D., Tavani, F.: Retrieval capabilities of hierarchical networks: from Dyson to Hopfield. Phys. Rev. Lett. 114(2), 028103 (2015)
Amit, D.J., Gutfreund, H., Sompolinsky, H.: Information storage in neural networks with low levels of activity. Phys. Rev. A 35, 2293–2303 (1987)
Derrida, B., Gardner, E., Zippelius, A.: An exactly solvable asymmetric neural network model. Europhys. Lett. 4, 167–173 (1987)
Dominguez, D., Koroutchev, K., Serrano, E., Rodríguez, F.B.: Information and topology in attractor neural network. Neural Comput. 19(4), 956–973 (2007)
Dominguez, D., González, M., Rodríguez, F.B., Serrano, E., Erichsen, R., Theumann, W.K.: Structured information in sparse-code metric neural networks. Phys. A: Stat. Mech. Appl. 391(3), 799–808 (2012). http://www.sciencedirect.com/science/article/pii/S0378437111007187
Dominguez, D., González, M., Serrano, E., Rodríguez, F.B.: Structured information in small-world neural networks. Phys. Rev. E 79(2), 021909 (2009)
Erdös, P., Rényi, A.: On random graphs. I. Publicationes Math. (Debrecen) 6, 290–297 (1959). http://www.renyi.hu/~p_erdos/Erdos.html#1959-11
González, M., Dominguez, D., Rodríguez, F.B.: Block attractor in spatially organized neural networks. Neurocomputing 72, 3795–3801 (2009)
Gonzalez, M., Dominguez, D., Rodriguez, F.B., Sanchez, A.: Retrieval of noisy fingerprint patterns using metric attractor networks. Int. J. Neural Syst. 24(07), 1450025 (2014)
González, M., Dominguez, D., Sánchez, Á.: Learning sequences of sparse correlated patterns using small-world attractor neural networks: an application to traffic videos. Neurocomputing 74(14–15), 2361–2367 (2011). http://www.sciencedirect.com/science/article/pii/S092523121100155X
González, M., Dominguez, D., Sánchez, A., Rodríguez, F.B.: Increase attractor capacity using an ensembled neural network. Expert Syst. Appl. 71, 206–215 (2017). http://www.sciencedirect.com/science/article/pii/S0957417416306704
González, M., del Mar Alonso-Almeida, M., Avila, C., Dominguez, D.: Modeling sustainability report scoring sequences using an attractor network. Neurocomputing 168, 1181–1187 (2015). http://www.sciencedirect.com/science/article/pii/S0925231215006219
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA 79(8), 2554–2558 (1982). http://www.pnas.org/cgi/content/abstract/79/8/2554
Sollich, P., Tantari, D., Annibale, A., Barra, A.: Extensive parallel processing on scale-free networks. Phys. Rev. Lett. 113(23), 238106 (2014)
Acknowledgments
This work was funded by the Spanish projects of Ministerio de Economía y Competitividad TIN-2010-19607, TIN2014-54580-R, TIN2014-57458-R (http://www.mineco.gob.es/); and UNEMI-2016-CONV-P-01-01 and DITC-UDLA, Ecuador. The funders had no role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
González, M., Dominguez, D., Sánchez, Á., Rodríguez, F.B. (2017). 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) Advances in Computational Intelligence. IWANN 2017. Lecture Notes in Computer Science(), vol 10305. Springer, Cham. https://doi.org/10.1007/978-3-319-59153-7_43
Download citation
DOI: https://doi.org/10.1007/978-3-319-59153-7_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59152-0
Online ISBN: 978-3-319-59153-7
eBook Packages: Computer ScienceComputer Science (R0)