Abstract
Population based decision mechanisms employed by many Swarm Intelligence methods can suffer poor convergence resulting in ill-defined halting criteria and loss of the best solution. Conversely, as a result of its resource allocation mechanism, the solutions found by Stochastic Diffusion Search enjoy excellent stability. Previous implementations of SDS have deployed complex stopping criteria derived from global properties of the agent population; this paper examines two new local SDS halting criteria and compares their performance with ‘quorum sensing’ - a natural termination criterion deployed in nature by some species of tandem-running ants. We empirically demonstrate that local termination criteria are almost as robust as the classical SDS termination criteria, whilst the average time taken to reach a decision is around three times faster.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Standard SDS has previously been shown to be a global search algorithm [26] - it will eventually converge to the global best solution in a given search space; by removing agents form the swarm, relative to standard SDS the number of potential agents remaining available for explore-exploit behaviour is reduced; precisely how this reduction impacts the robustness of the algorithm [with respect to erroneous convergence to sub-optimal solutions] has yet to be fully established.
- 2.
To facilitate the use of homogenous performance metrics, we assume that in a population of k agents, k single asynchronous updates corresponds to one standard synchronous iteration cycle.
- 3.
Temnothorax ants are indeed sometimes recruited back to nests they have already visited, so there is potential for this ‘reinforcement recruitment’ process to play a role for ant colonies. For example, ‘reinforcement recruitment’ could cause ants to enter a post-quorum state at a lowered encounter rate. This would help extra rapid acceptance of a nest if there were only one new nest site available. This idea could be tested empirically, ideally in a complex arena that would promote tandem-running behaviour, allowing communication of preference.
- 4.
\(\beta \) defines a “uniform random noise” hypothesis; an aggregate of all the possible hypotheses an agent could have other than the putative solution hypothesis.
- 5.
These parameters define a problem analogous to the search space being infinitely large, wherein the only way an agent can adopt the ‘best’ solution is to receive it via diffusion from an active agent.
References
Aleksander, I., Stonham, T.J.: Guide to pattern recognition using random access memories. Comput. Digital Tech. 2(1), 29–40 (1979)
al-Rifaie, M.M., Bishop, J.M.: Stochastic diffusion search review. J. Behav. Robot. 4(3), 155–173 (2013)
Anoop, K., Sumana, A.: Response to a change in the target nest during ant relocation. J. Exp. Biol. 218(6), 887–892 (2015)
Arthur, W.B.: Inductive reasoning and bounded rationality, (The El Farol Problem). Amer. Econ. Rev. 84, 406–411 (1994)
Back, T.: Evolutionary Algorithms in Theory and Practice. Oxford University Press, Oxford (1996)
Beattie, P.D., Bishop, J.M.: Self-localisation in the ‘SENARIO’ autonomous wheelchair. J. Intell. Robot. Syst. 22, 255–267 (1998)
Bishop, J.M.: Stochastic searching networks. In: Proceedings of 1st IEE International Conference Artificial Neural Networks, IEE Conference Publication, vol. 313, pp. 329–331. IEE, London (1989)
Bishop, J.M., Torr, P.H.S.: The stochastic search network. In: Linggard, R., Myers, D.J., Nightingale, C. (eds.) Neural Networks for Images, Speech and Natural Language. Chapman Hall, New York (1992)
Bishop, J.M., Nasuto, S.J., De Meyer, K.: Dynamic knowledge representation in connectionist systems. In: Dorronsoro, J.R. (ed.) ICANN 2002. LNCS, vol. 2415, pp. 308–313. Springer, Heidelberg (2002)
Bonabeau, E., Dorigo, M., Theraulaz, G.: Swarm Intelligence: from Natural to Artificial Systems. Oxford University Press, Oxford (1999)
Cao, T.T.: High social density increases foraging and scouting rates and induces polydomy in Temnothorax ants. Behav. Ecol. Sociobiol. 67(11), 1799–1807 (2013)
Dornhaus, A., Franks, N.R., Hawkins, R.M., Shere, H.N.S.: Ants move to improve: colonies of Leptothorax albipennis emigrate whenever they find a superior nest site. Anim. Behav. 67(5), 959–963 (2004)
Dornhaus, A., Holley, J.A., Pook, V.G., Worswick, G., Franks, N.R.: Why do not all workers work? colony size and workload during emigrations in the ant Temnothorax albipennis. Behav. Ecol. Sociobiol. 63(1), 43–51 (2008)
Franklin, E.L.: The journey of tandem running: the twists, turns and what we have learned. Insectes Soc. 61, 1–8 (2014)
Franks, N.R., Hooper, J.W., Gumn, M., Bridger, T.H., Marshall, J.A.R., Gro, R., Dornhaus, A.: Moving targets: collective decisions and flexible choices in house-hunting ants. Swarm Intell. 1(2), 81–94 (2007)
Franks, N.R., Mallon, E.B., Bray, H.E., Hamilton, M.J., Mischler, T.C.: Strategies for choosing between alternatives with different attributes: exemplified by house-hunting ants. Anim. Behav. 65, 215–223 (2003)
Franks, N.R., Stuttard, J.P., Doran, C., Esposito, J.C., Master, M.C., Sendova-Franks, A.B., Masuda, N., Britton, N.F.: How ants use quorum sensing to estimate the average quality of a fluctuating resource. Sci. Rep. 5, 11890 (2015)
Goldberg, D.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison Wesley, Reading (1989)
Grech-Cini, E.: Locating facial features. Ph.D. dissertation, University of Reading, Reading (1995)
Holland, J.H.: Adaptation in Natural and Artificial Systems. The University of Michigan Press, Ann Arbor (1975)
Kennedy, J., Eberhart, R.C., Shi, Y.: Swarm Intelligence. Morgan Kauffman, San Francisco (2001)
Kramer, B.H., Scharf, I., Foitzik, S.: The role of per-capita productivity in the evolution of small colony sizes in ants. Behav. Ecol. Sociobiol. 68(1), 41–53 (2013)
De Meyer, K., Nasuto, S.J., Bishop, J.M.: Stochastic diffusion optimisation: the application of partial function evaluation and stochastic recruitment. In: Abraham, A., Grosam, C., Ramos, V. (eds.) Stigmergic Optimization. Studies in Computational Intelligence, vol. 31, pp. 185–207. Springer, Heidelberg (2006)
Myatt, D., Nasuto, S.J., Bishop J.M.: Alternative recruitment strategies for SDS. In: Proceedings AISB06: Symposium on Exploration vs. Exploitation in Naturally Inspired Search, pp. 181–187. Bristol, UK (2006)
Nasuto, S.J.: Analysis of resource allocation of stochastic diffusion search. Ph.D. dissertation, University of Reading, Reading, UK (1999)
Nasuto, S.J., Bishop, J.M.: Convergence of the stochastic diffusion search. Parallel Algorithms Appl. 14, 89–107 (1999)
Nasuto, S.J., Bishop, J.M., Lauria, S.: Time complexity of stochastic diffusion search. In: Heiss, M. (ed.) Proceeding International ICSC/IFAC Symposium on Neural Computation, Vienna (1998)
Nasuto, S.J., Dautenhahn, K., Bishop, J.M.: Communication as an emergent methaphor for neuronal operation. In: Nehaniv, C. (ed.) Computation for Metaphors, Analogy, and Agents. LNAI, vol. 1562, pp. 365–379. Springer, Heidelberg (1999)
Nasuto, S.J., Bishop, J.M., De Meyer, K.: Communicating neurons: a connectionist spiking neuron implementation of stochastic diffusion search. Neurocomputing 72(4–6), 704–712 (2008)
Pratt, S.C.: Behavioral mechanisms of collective nest-site choice by the ant Temnothorax curvispinosus. Insectes Soc. 52, 383–392 (2005)
Pratt, S.C.: Quorum sensing by encounter rates in the ant Temnothorax albipennis. Behav. Ecol. 16, 488–496 (2005)
Pratt, S.C., Mallon, E.B., Sumpter, D.J.T., Franks, N.R.: Quorum sensing, recruitment, and collective decision-making during colony emigration by the ant Leptothorax albipennis. Behav. Ecol. Sociobiol. 52(2), 117–127 (2002)
Pratt, S.C., Pierce, N.E.: The cavity-dwelling ant Leptothorax curvispinosus uses nest geometry to discriminate among potential homes. Anim. Behav. 62, 281–287 (2001)
Pratt, S.C., Sumpter, D.J.T., Mallon, E.B., Franks, N.R.: An agent-based model of collective nest site choice by the ant Temnothorax albipennis. Anim. Behav. 70, 1023–1036 (2005)
Robinson, E.J.H., Feinerman, O., Franks, N.R.: How collective comparisons emerge without individual comparisons of the options. Proc. Royal Soc. B 281, 20140737 (2014). doi:10.1098/rspb.2014.0737
Robinson, E.J.H., Franks, N.R., Ellis, S., Okuda, S., Marshall, J.A.R.: A simple threshold rule is sufficient to explain sophisticated collective decision-making. PLoS One 6, e19981 (2011)
Robinson, E.J.H., Smith, F.D., Sullivan, K.M.E., Franks, N.R.: Do ants make direct comparisons? Proc. Royal Soc. B 276, 2635–2641 (2009)
Seeley, T.D., Visscher, P.K., Schlegel, T., Hogan, P.M., Franks, N.R., Marshall, J.A.R.: Stop signals provide cross inhibition in collective decision-making by honey bee swarms. Science 335, 108–111 (2012)
Stroeymeyt, N., Robinson, E.J.H., Hogan, P.M., Marshall, J.A.R., Giurfa, M., Franks, N.R.: Experience-dependent flexibility in collective decision-making by house-hunting ants. Behav. Ecol. 22(3), 535–542 (2011)
Sumpter, D.J.T., Pratt, S.C.: Quorum responses and consensus decision making. Proc. Royal Soc. B 364(1518), 743–753 (2009)
Whitaker, R.M., Hurley, S.: An agent based approach to site selection for wireless networks. In: Proceeding 2002 ACM Symposium Applied Computing (Madrid), pp. 574–577. ACM, New York (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Bishop, J.M., Martin, A.O., Robinson, E.J.H. (2016). Local Termination Criteria for Stochastic Diffusion Search: A Comparison with the Behaviour of Ant Nest-Site Selection. In: Nguyen, NT., Iliadis, L., Manolopoulos, Y., Trawiński, B. (eds) Computational Collective Intelligence. ICCCI 2016. Lecture Notes in Computer Science(), vol 9875. Springer, Cham. https://doi.org/10.1007/978-3-319-45243-2_44
Download citation
DOI: https://doi.org/10.1007/978-3-319-45243-2_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-45242-5
Online ISBN: 978-3-319-45243-2
eBook Packages: Computer ScienceComputer Science (R0)