Self-Organization and Templates: Application to Data Analysis and Graph Partitioning

Author(s):  
Eric Bonabeau ◽  
Marco Dorigo ◽  
Guy Theraulaz

The biological phenomena described in the previous chapter were corpse aggregation and brood sorting by ants. The clusters of items obtained with the models introduced in sections 4.3.1 and 4.3.2 emerged at arbitrary locations. The underlying self-organizing process, whereby large clusters grow even larger because they are more attractive than smaller clusters, does not ensure the formation of clusters at specific locations. In the two biological examples described in this chapter, the self-organizing dynamics of aggregation is constrained by templates. A template is a pattern that is used to construct another pattern. The body of a termite queen or a brood pile in ants are two examples of structures—the second one resulting from the activities of the colony—that serve as templates to build walls. Walls built around the termite queen form the royal chamber; walls built around the brood pile form the ant nest. When a mechanism combines self-organization and templates, it exhibits the characteristic properties of self-organization, such as snowball effect or multistability, and at the same time produces a perfectly predictable pattern that follows the template. The two nonparametric algorithms presented in chapter 4, one for multidimensional scaling and the other for graph partitioning, can be made parametric through the use of templates. The number of clusters of data points or vertices can be predefined by forcing items to be deposited in a prespecified number of regions in the space of representation, so that the number of clusters and their locations are known in advance. In the previous chapter, we saw how the attractivity of corpses or the differential attractivity of items of different types could lead to the formation of clusters of specific items. Self-organization lies in this attractivity, which induces a snowball effect: the larger a cluster, the more likely it is to attract even more items. But selforganization can also be combined with a template mechanism in the process of clustering. A template is a kind of prepattern in the environment, used by insects— or by other animals—to organize their activities.

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Baicheng Lyu ◽  
Wenhua Wu ◽  
Zhiqiang Hu

AbstractWith the widely application of cluster analysis, the number of clusters is gradually increasing, as is the difficulty in selecting the judgment indicators of cluster numbers. Also, small clusters are crucial to discovering the extreme characteristics of data samples, but current clustering algorithms focus mainly on analyzing large clusters. In this paper, a bidirectional clustering algorithm based on local density (BCALoD) is proposed. BCALoD establishes the connection between data points based on local density, can automatically determine the number of clusters, is more sensitive to small clusters, and can reduce the adjusted parameters to a minimum. On the basis of the robustness of cluster number to noise, a denoising method suitable for BCALoD is proposed. Different cutoff distance and cutoff density are assigned to each data cluster, which results in improved clustering performance. Clustering ability of BCALoD is verified by randomly generated datasets and city light satellite images.


2021 ◽  
Author(s):  
BAICHENG LV ◽  
WENHUA WU ◽  
ZHIQIANG HU

Abstract With the widely application of cluster analysis, the number of clusters is gradually increasing, as is the difficulty in selecting the judgment indicators of cluster numbers. Also, small clusters are crucial to discovering the extreme characteristics of data samples, but current clustering algorithms focus mainly on analyzing large clusters. In this paper, a bidirectional clustering algorithm based on local density (BCALoD) is proposed. BCALoD establishes the connection between data points based on local density, can automatically determine the number of clusters, is more sensitive to small clusters, and can reduce the adjusted parameters to a minimum. On the basis of the robustness of cluster number to noise, a denoising method suitable for BCALoD is proposed. Different cutoff distance and cutoff density are assigned to each data cluster, which results in improved clustering performance. Clustering ability of BCALoD is verified by randomly generated datasets and city light satellite images.


Author(s):  
Stuart P. Wilson

Self-organization describes a dynamic in a system whereby local interactions between individuals collectively yield global order, i.e. spatial patterns unobservable in their entirety to the individuals. By this working definition, self-organization is intimately related to chaos, i.e. global order in the dynamics of deterministic systems that are locally unpredictable. A useful distinction is that a small perturbation to a chaotic system causes a large deviation in its trajectory, i.e. the butterfly effect, whereas self-organizing patterns are robust to noise and perturbation. For many, self-organization is as important to the understanding of biological processes as natural selection. For some, self-organization explains where the complex forms that compete for survival in the natural world originate from. This chapter outlines some fundamental ideas from the study of simulated self-organizing systems, before suggesting how self-organizing principles could be applied through biohybrid societies to establish new theories of living systems.


2021 ◽  
Vol 7 (16) ◽  
pp. eabe3801
Author(s):  
Amanda J. Ackroyd ◽  
Gábor Holló ◽  
Haridas Mundoor ◽  
Honghu Zhang ◽  
Oleg Gang ◽  
...  

Chemical organization in reaction-diffusion systems offers a strategy for the generation of materials with ordered morphologies and structural hierarchy. Periodic structures are formed by either molecules or nanoparticles. On the premise of new directing factors and materials, an emerging frontier is the design of systems in which the precipitation partners are nanoparticles and molecules. We show that solvent evaporation from a suspension of cellulose nanocrystals (CNCs) and l-(+)-tartaric acid [l-(+)-TA] causes phase separation and precipitation, which, being coupled with a reaction/diffusion, results in rhythmic alternation of CNC-rich and l-(+)-TA–rich rings. The CNC-rich regions have a cholesteric structure, while the l-(+)-TA–rich bands are formed by radially aligned elongated bundles. The moving edge of the pattern propagates with a finite constant velocity, which enables control of periodicity by varying film preparation conditions. This work expands knowledge about self-organizing reaction-diffusion systems and offers a strategy for the design of self-organizing materials.


2007 ◽  
Vol 11 (04) ◽  
pp. 277-286 ◽  
Author(s):  
Mihaela Carmen Balaban ◽  
Teodor Silviu Balaban

Two new zinc porphyrins having two meso-undecyl solubilizing groups and two meso-formyl groups or two meso-cyano groups have been prepared in good yields and were shown by stationary absorption and fluorescence spectroscopies to self-organize in nonpolar solvents such as n-heptane. The diformyl and dicyano recognition groups can thus successfully replace the hydroxy and carbonyl recognition groups encountered in the natural self-organizing bacteriochlorophylls and which were, up to now, the only recognition groups used in synthetic or semisynthetic bacteriochlorophyll mimics.


2019 ◽  
Vol 47 (2) ◽  
pp. 220-234 ◽  
Author(s):  
Stefano Moroni ◽  
Ward Rauws ◽  
Stefano Cozzolino

The implications of self-organizing phenomena for planning strategies and interventions are a relatively new topic of research that is gaining increasing traction with urban planners and the emerging literature. The problem is that the concept of self-organization is at present applied in a variety of different ways in the contemporary planning debate, a fact that has generated misunderstandings, dubious definitions, and questionable practical suggestions. The aim of this article is to (1) unravel this complex issue by differentiating urban phenomena that are usually all labeled as self-organizing; (2) identify which of them is the most challenging for planning theory and practice, and (3) discuss how planning can productively relate to this form of self-organization.


2013 ◽  
Vol 16 (02n03) ◽  
pp. 1350001 ◽  
Author(s):  
GEORG MARTIUS

Self-organizing processes are crucial for the development of living beings. Practical applications in robots may benefit from the self-organization of behavior, e.g., to increase fault tolerance and enhance flexibility, provided that external goals can also be achieved. We present results on the guidance of self-organizing control by visual target stimuli and show a remarkable robustness to sensorimotor disruptions. In a proof of concept study an autonomous wheeled robot is learning an object finding and ball-pushing task from scratch within a few minutes in continuous domains. The robustness is demonstrated by the rapid recovery of the performance after severe changes of the sensor configuration.


Author(s):  
Margaret A. Boden

Artificial life (A-Life) models biological systems. Like AI, it has both technological and scientific aims. ‘Robots and artificial life’ explains that A-Life is integral to AI, because all the intelligence we know about is found in living organisms. AI technologists turn to biology in developing practical applications of many kinds, including robots, evolutionary programming, and self-organizing devices. Robots are quintessential examples of AI, having high visibility and being hugely ingenious—and very big business, too. Evolutionary AI, although widely used, is less well known. Self-organizing machines are even less familiar. Nevertheless, in the quest to understand self-organization, AI has been as useful to biology as biology has been to AI.


Sign in / Sign up

Export Citation Format

Share Document