Abstract
While self-assembly is a fairly active area of research in swarm intelligence, relatively little attention has been paid to the issues surrounding the construction of network structures. In this paper we extend methods developed previously for controlling collective movements of agent teams to serve as the basis for self-assembly or “growth” of networks, using neural networks as a concrete application to evaluate our approach. Our central innovation is having network connections arise as persistent “trails” left behind moving agents, trails that are reminiscent of pheromone deposits made by agents in ant colony optimization models. The resulting network connections are thus essentially a record of agent movements. We demonstrate our model’s effectiveness by using it to produce two large networks that support subsequent learning of topographic and feature maps. Improvements produced by the incorporation of collective movements are also examined through computational experiments. These results indicate that methods for directing collective movements can be adopted to facilitate network self-assembly.
Similar content being viewed by others
References
Arbuckle, D., & Requicha, A. (2004). Active self-assembly. In Proceedings of the IEEE international conference on robotics and automation (ICRA’04) (pp. 896–901). New York: IEEE.
Astor, J. C., & Adami, C. (2000). A developmental model for the evolution of artificial neural networks. Artificial Life, 6, 189–218.
Bishop, J., Burden, S., Klavins, E., et al. (2005). Programmable parts: A demonstration of the grammatical approach to self-organization. In Proceedings of the IEEE international conference on intelligent robots and systems (IROS’05) (pp. 3684–3691). New York: IEEE.
Bonabeau, E., Dorigo, M., & Theraulaz, G. (1999). Swarm intelligence: from natural to artificial systems. London: Oxford University Press.
Cangelosi, A., Parisi, D., & Nolfi, S. (1994). Cell division and migration in a “genotype” for neural networks. Network: Computation in Neural Systems, 5, 497–515.
Chval, J. (2002). Evolving artificial neural networks by means of evolutionary algorithms with L-systems based encoding (Research Report). Prague, Czech Republic: Czech Technical University.
Delgado, A. (2000). Control of nonlinear systems using a self-organizing neural network. Neural Computing & Applications, 9(2), 113–123.
Deneubourg, J.-L., Goss, S., Franks, N., & Pasteels, J.-M. (1989). The blind leading the blind: modelling chemically mediated army ant raid patterns. Journal of Insect Behavior, 2, 719–725.
Deneubourg, J.-L., Aron, S., Goss, S., & Pasteels, J.-M. (1990). The self-organizing exploratory pattern of the Argentine ant. Journal of Insect Behavior, 3, 159–168.
Eggenberger, P. (1997). Creation of neural networks based on developmental and evolutionary principles. In W. Gerstner, A. Germond, M. Hasler, & J. Nicoud (Eds.), Proceedings of the international conference on artificial neural networks (ICANN’97) (pp. 337–342). Berlin/Heidelberg: Springer.
Elizondo, E., Birkenhead, R., Góngora, M., et al. (2007). Analysis and test of efficient methods for building recursive deterministic perceptron neural networks. Neural Networks, 20, 1095–1108.
Fahlman, S., & Lebiere, C. (1990). The cascade-correlation learning architecture. In D. S. Touretzky (Ed.), Advances in neural information processing systems II (pp. 524–532). San Mateo: Morgan Kaufmann.
Farkaš, I., & Miikkulainen, R. (1999). Modeling the self-organization of directional selectivity in the primary visual cortex. In D. Willshaw, & A. Murray (Eds.), Proceedings of the international conference on artificial neural networks (ICANN’99) (pp. 251–256). London: IEE.
Fleischer, K. (1995). A multiple-mechanism developmental model for defining self-organizing geometric structures (Dissertation). Pasadena, CA: California Institute of Technology.
Fleischer, K., & Barr, A. (1994). A simulation testbed for the study of multicellular development: the multiple mechanisms of morphogenesis. In C. G. Langton (Ed.), SFI studies in the science of complexity: Vol. XVII. Artificial life III (pp. 389–416). Reading: Addison-Wesley.
Franks, N., Gomez, N., Goss, S., & Deneubourg, J.-L. (1991). The blind leading the blind in army ant raid patterns: testing a model of self-organization (Hymenoptera: Formicidae). Journal of Insect Behavior, 4, 583–607.
Frean, M. (1990). The upstart algorithm: a method for constructing and training feedforward neural networks. Neural Computation, 2, 198–209.
Goodhill, G., & Xu, J. (2005). The development of retinotectal maps: a review of models based on molecular gradients. Network, 16, 5–34.
Goodhill, G., Gu, M., & Urbach, J. (2004). Predicting axonal response to molecular gradients with a computational model of filopodial dynamics. Neural Computation, 16, 2221–2243.
Gracias, D., Tien, J., Breen, T., Hsu, C., & Whitesides, G. (2000). Forming electrical networks in three dimensions by self-assembly. Science, 289, 1170–1172.
Gross, R., Bonani, M., Mondala, F., & Dorigo, M. (2006). Autonomous self-assembly in swarm-bots. IEEE Transactions on Robotics, 22, 1115–1130.
Grove, E., & Fukuchi-Shimogori, T. (2003). Generating the cerebral cortical area map. Annual Review of Neuroscience, 26, 355–380.
Gruau, F. (1993). Genetic synthesis of modular neural networks. In S. Forest (Ed.), Proceedings of the 5th international conference on genetic algorithms (ICGA’93) (pp. 318–325). San Mateo: Morgan Kaufmann.
Grushin, A., & Reggia, J. (2006). Stigmergic self-assembly of prespecified artificial structures in a constrained and continuous environment. Integrated Computer-Aided Engineering, 13, 289–312.
Grushin, A., & Reggia, J. (2008). Automated design of distributed control rules for the self-assembly of pre-specified artificial structures. Robotics and Autonomous Systems, 56, 334–359.
Haessly, A., Sirosh, J., & Miikkulainen, R. (1995). A model of visually guided p lasticity of the auditory spatial map in the barn owl. In J.F. Lehman & J.D. Moore (Eds.), Proceedings of the 17th annual meeting of the cognitive science society (pp. 154–158). Hillsdale: Erlbaum.
Haykin, S. (1999). Neural networks: a comprehensive foundation (2nd edn). New York: Prentice-Hall.
Hentschel, H., & van Ooyen, A. (1999). Models of axon guidance and bundling during development. Proceedings of the Royal Society (London) B, 266, 2231–2238.
Honda, H. (2003). Competition between retinal ganglion axons for targets under the servomechanism model. Journal of Neuroscience, 23(1999), 10368–10377.
Jones, C., & Matarić, M. (2003). From local to global behavior in intelligent self-assembly. In Proceedings of the IEEE international conference on robotics and automation (ICRA’03) (pp. 721–726). New York: IEEE.
Jung, J., & Reggia, J. (2006). Evolutionary design of neural network architectures using a descriptive encoding language. IEEE Transactions on Evolutionary Computation, 10, 676–688.
Kalay, A., Parnas, H., & Shamir, E. (1995). Neuronal growth via hybrid system of self-growing and diffusion based grammar rules: I. Bulletin of Mathematical Biology, 57, 205–227.
Kennedy, J., & Eberhart, R. (1995). Particle swarm optimization. In Proceedings of the IEEE international conference on neural networks (pp. 1942–1948). New York: IEEE.
Kitano, H. (1990). Designing neural networks using genetic algorithms with graph generation system. Complex Systems, 4, 461–476.
Klavins, E. (2007). Programmable self-assembly. IEEE Control Systems Magazine, 27, 43–56.
Klavins, E., Ghrist, R., & Lipsky, D. (2004). Graph grammars for self-assembling robotic systems. In Proceedings of the IEEE international conference on robotics and automation (ICRA’04) (pp. 5293–5300). New York: IEEE.
Kohonen, T. (2001). Self-organizing maps. New York: Springer.
LeCun, Y., Denker, J., & Solla, S. (1990). Optimal brain damage. In D. Touretzky (Ed.), Advances in neural information processing systems II (pp. 598–605). San Mateo: Morgan Kaufmann.
Lendasse, A., Verleysen, M., de Bodt, E., Gregoire, P., & Cottrell, M. (1998). Forecasting time-series by Kohonen classification. In M. Verleysen (Ed.), Proceedings of the 6th European symposium on artificial neural networks (ESANN’98) (pp. 221–226). Brussels: D-Facto public.
Lopez-Bendito, G., & Molnar, Z. (2003). Thalamocortical development: how are we going to get there? Nature Reviews Neuroscience, 4, 276–289.
von der Malsburg, C. (1973). Self-organization of orientation sensitive cells in the striate cortex. Kybernetik, 14, 85–100.
Marchand, M., Golea, M., & Rujan, P. (1990). A convergence theorem for sequential learning in two-layer perceptrons. Europhysics Letters, 11(6), 487–492.
Nembrini, J., Reeves, N., Poncet, E., et al. (2005). Flying swarm intelligence for architectural research. In Proceedings of the IEEE swarm intelligence symposium (SIS’05) (pp. 225–232). New York: IEEE.
van Ooyen, A. (1994). Activity-dependent neural network development. Network: Computation in Neural Systems, 5, 401–423.
Pearson, J., Finkel, L., & Edelman, G. (1987). Plasticity in the organization of adult cerebral cortical maps: a computer simulation, based on neuronal group, selection. The Journal of Neuroscience, 7, 4209–4223.
Prusinkiewicz, P., & Lindenmayer, A. (1990). The algorithmic beauty of plants. New York: Springer.
Pulakka, K., & Kujanpa, V. (1998). Rough level path planning method for a robot using SOFM neural network. Robotica, 16, 415–423.
Reggia, J., & Martin, C. (2009). Self-assembly of a neural network. College Park, Univ. of Maryland, Dept. of Computer Science. http://www.cs.umd.edu/~reggia/martin.html.
Reynolds, C. (1987). Flocks, herds, and schools: a distributed behavioral model. Computer Graphics, 21(4), 25–34.
Ritter, H., Martinetz, T., & Schulten, K. (1992). Neural computation and self-organizing maps. Reading: Addison-Wesley.
Rodriguez, A., & Reggia, J. (2004). Extending self-organizing particle systems to problem solving. Artificial Life, 10, 379–395.
Rust, A., Adams, R., Schilstra, M., & Bolouri, H. (2003). Evolving computational neural systems using synthetic developmental mechanisms. In S. Kumar & P. Bentley (Eds.), On growth, form and computers (pp. 353–376). San Diego: Academic Press.
Spitzer, N. (2006). Electrical activity in early neuronal development. Nature, 444, 707–712.
Sutton, G., Reggia, J., Armentrout, S., & D’Autrechy, C. (1994). Cortical map reorganization as a competitive process. Neural Computation, 6, 1–13.
Vesanto, J. (1999). SOM-based data visualization methods. Intelligent Data Analysis, 3, 111–126.
Vesanto, J., & Alhoniemi, E. (2000). Clustering of the self-organizing map. IEEE Transactions on Neural Networks, 11(3), 586–600.
Werfel, J., & Nagpag, R. (2006). Extended stigmergy in collective construction. IEEE Intelligent Systems, 21, 20–28.
White, P., Zykov, V., Bongard, J., & Lipson, H. (2005). Three dimensional stochastic reconfiguration of modular robots. In Proceedings of robotics: science and systems (pp. 161–168). Cambridge: MIT Press.
Whitesides, G., & Gzybowski, B. (2002). Self-assembly at all scales. Science, 295, 2418–2421.
Yates, P., Holub, A., McLaughlin, T., et al. (2004). Computational modeling of retinotopic map development to define contributions of EphA-EphrinA gradients, axon–axon interactions, and patterned activity. Journal of Neurobiology, 59, 95–113.
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported in part by NSF Awards ITS-0325089 and DMS-0240049.
Electronic Supplementary Material
Rights and permissions
About this article
Cite this article
Martin, C.E., Reggia, J.A. Self-assembly of neural networks viewed as swarm intelligence. Swarm Intell 4, 1–36 (2010). https://doi.org/10.1007/s11721-009-0035-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11721-009-0035-7