Artificial Creativity of Evolutionary Swarm Systems

Sep 25, 20181 like137 views

This document describes research on an artificial system that exhibits creative behavior through evolutionary swarm interactions. The system consists of particles that interact locally based on kinetic parameters and compete to transmit their "recipes" to other particles. Over many iterations, this leads to the spontaneous emergence of diverse stable object patterns in the environment. Subjecting the system to different levels of environmental perturbations influenced the size and color diversity of the evolved objects. The researcher argues this bottom-up approach offers a novel path to machine creativity without direct optimization of a global fitness function.

Artificial Creativity of
Evolutionary Swarm Systems
Hiroki Sayama
Center for Collective Dynamics of Complex Systems
Binghamton University, State University of New York
sayama@binghamton.edu

https://www.oreilly.com/ideas/open-endedness-
the-last-grand-challenge-youve-never-heard-of
2

Swarm
Chemistry
http://bingweb.binghamton.edu/~sayama/SwarmChemistry/
3

i
• Particles in a continuous open 2-D space
• Kinetic interactions with local neighbors
• No capability to distinguish different types
Model Assumptions
4

Kinetic Parameters
(Assigned to each particle individually)
5

i
Cohesion Alignment Separation
97 * (226.76, 3.11, 9.61, 0.15, 0.88, 43.35, 0.44, 1.0 )
38 * ( 57.47, 9.99, 35.18, 0.15, 0.37, 30.96, 0.05, 0.31)
56 * ( 15.25, 13.58, 3.82, 0.3, 0.8, 39.51, 0.43, 0.65)
31 * (113.21, 18.25, 38.21, 0.62, 0.46, 15.78, 0.49, 0.61)
Recipe
6

Artificial Creativity of Evolutionary Swarm Systems

Recipe Competition Between Active Particles
Competition between active particles
97 * (226.76, 3.11, 9.61, 0.15, 0.88, 43.35, 0.44, 1.0)
38 * (57.47, 9.99, 35.18, 0.15, 0.37, 30.96, 0.05, 0.31)
56 * (15.25, 13.58, 3.82, 0.3, 0.8, 39.51, 0.43, 0.65)
31 * (113.21, 18.25, 38.21, 0.62, 0.46, 15.78, 0.49, 0.61)
67 * (216.35, 11.75, 7.7, 0.83, 0.97, 97.31, 0.02, 0.38)
29 * (254.64, 7.28, 7.0, 0.95, 0.11, 22.41, 0.43, 0.31)
13 * (105.4, 3.55, 5.24, 0.34, 0.18, 23.53, 0.39, 0.24)
competition
function
winner:
8

97 * (226.76, 3.11, 9.61, 0.15, 0.88, 43.35, 0.44, 1.0)
38 * (57.47, 9.99, 35.18, 0.15, 0.37, 30.96, 0.05, 0.31)
56 * (15.25, 13.58, 3.82, 0.3, 0.8, 39.51, 0.43, 0.65)
31 * (113.21, 18.25, 38.21, 0.62, 0.46, 15.78, 0.49, 0.61)
Mutations
Recipe transmission & mutation
75 * (216.35, 11.75, 7.7, 0.83, 0.97, 97.31, 0.02, 0.38)
29 * (254.64, 7.28, 7.0, 0.95, 0.11, 28.56, 0.43, 0.31)
13 * (105.4, 3.55, 5.24, 0.34, 0.18, 23.53, 0.39, 0.24)
9
67 * (216.35, 11.75, 7.7, 0.83, 0.97, 97.31, 0.02, 0.38)
29 * (254.64, 7.28, 7.0, 0.95, 0.11, 22.41, 0.43, 0.31)
13 * (105.4, 3.55, 5.24, 0.34, 0.18, 23.53, 0.39, 0.24)

Sayama, IEEE ALIFE (2011) Sayama & Wong, ECAL (2011)
Is This Really Creative?

Simulate It Much Longer
Detect Objects Automatically

Environmental Perturbations
• Competition function switched from
“majority-relative” to either “faster”
or “slower” for T steps in every 2000
steps in either half of the space
T = 50 (short, moderate)
T = 500 (long, severe)

Detailed Object Tracking (Object Size)
With moderate environmental perturbations
Objects tend
to get bigger
over time

Detailed Object Tracking (Object Size)
With moderate environmental perturbations With severe environmental perturbations
But it also depends on the
severity of perturbations

Detailed Object Tracking (Color Diversity)
With moderate environmental perturbations With severe environmental perturbations
Severe perturbations may increase
color entropy of objects

Conclusions
Evolutionary swarm chemistry
can produce patterns with no
global fitness evaluation
The “bottom-up” approach
offers a unique path to
machine creativity
Automated object harvesting
has captured a large number
of patterns

The document describes a study that tested whether muscle synergies underlie active perception of force. Participants judged if an upward force was applied to their forearm while maintaining posture. A model based on modulation of elbow and shoulder muscle synergies (MSM) explained about 70% of participants' ability to perceive force, compared to 50% for a model of individual muscle activity. The findings provide evidence that motor synergies involved in the task underlie force perception, suggesting synergies simplify sampling of relevant sensory inputs.

Finit element in prosthodontics /certified fixed orthodontic courses by India...Indian dental academy

��

Artificial Intelligence, Machine Learning, and (Large) Language Models: A Qui...Hiroki Sayama

��

A Quick Overview of Artificial Intelligence and Machine Learning (revised ver...Hiroki Sayama

��

This document provides an overview of artificial intelligence and machine learning. It discusses early concepts of intelligence and key contributors. Statistics, data analytics, and optimization are identified as important ingredients. Machine learning techniques like supervised learning, unsupervised learning, and reinforcement learning are explained. Neural networks including recurrent neural networks and deep learning are covered. Research examples and challenges in the field are also summarized.

A Quick Overview of Artificial Intelligence and Machine LearningHiroki Sayama

��

How to Make Things EvolveHiroki Sayama

��

Review of linear algebraHiroki Sayama

��

What an ALifer Has Been Doing About COVID-19Hiroki Sayama

��

1) An ALifer at Binghamton University helped with several COVID-19 modeling projects in response to the pandemic, including campus traffic modeling, campus epidemic modeling, and county-level and nationwide visualization projects. 2) The campus traffic modeling used an agent-based model to simulate pedestrian and vehicle movement and measure close contacts on a typical day. The campus epidemic modeling estimated infection rates under different population densities. 3) The ALifer learned that applied work is more important than publications during a crisis, and that listening to frontline professionals is key. Modeling real situations requires collaboration across disciplines and adapting to rapid changes.

Self-organization of society: fragmentation, disagreement, and how to overcom...Hiroki Sayama

��

This document summarizes a presentation on self-organization of society. It discusses how social fragmentation, disagreement and extremism can emerge from decentralized interactions between individuals seeking conformity and homophily. Three recent papers are summarized that show how social networks can become polarized through adaptive dynamics, how enhanced information gathering can intensify disagreement, and how behavioral diversity among individuals can allow for both cultural diversity and network connectivity in society. The key messages are that individual and collective outcomes may not align, and behavioral heterogeneity presents opportunities for diverse yet cohesive social outcomes.

Enhanced ability of information gathering may intensify disagreement among gr...Hiroki Sayama

��

Complexity Explained: A brief intro to complex systemsHiroki Sayama

��

This document provides an introduction to complex systems. It defines complex systems as networks of many interacting components that can self-organize and show emergent behaviors. Examples of complex systems include ecosystems, economies, and the human brain. Research methods for studying complex systems include computer simulations, network modeling, and machine learning. Key concepts are interactions between parts, emergence of unexpected behaviors, dynamics and adaptation over time, and self-organization without centralized control. Both discovering patterns in data and building mechanistic models are important for understanding complex systems.

Graph product representation of organism-environment couplings in evolutionHiroki Sayama

��

This document presents a theoretical framework for modeling the evolution of organism-environment couplings using graph product multilayer networks. It describes how spatial and type diffusions between organism and environment nodes can be modeled as a single diffusion process on the graph product. The framework then models evolutionary dynamics as a reaction-diffusion process on this network, where local population dynamics are influenced by both inherent and environment-dependent fitnesses, and diffusion allows spatial and type mixing. Results demonstrate how the actual fitness of organisms depends on both their inherent fitness and the strength of spatial diffusion between environments.

Suppleness and Open-Endedness for Social SustainabilityHiroki Sayama

��

Adaptive network models of socio-cultural dynamicsHiroki Sayama

��

Effects of Organizational Network Structure and Task-Related Diversity on Col...Hiroki Sayama

��

This document summarizes an agent-based modeling study of how organizational network structure and task-related diversity affect collective design and innovation. The study finds that having more diverse expertise among agents and small-world network structures improve both the coverage of solutions in the problem space and the quality of final solutions. Increased network density can increase solution quality but decreases coverage. Future work includes making the model assumptions more realistic and conducting related human subject experiments.

How to survive as an interdisciplinary beingHiroki Sayama

��

Formulating Evolutionary Dynamics of Organism-Environment Couplings Using Gra...Hiroki Sayama

��

Self-Replication and the Halting ProblemHiroki Sayama

��

Von Neumann proposed that an artificial self-replicating system would require a universal constructor that can build copies of itself by reading its own description. This is analogous to Turing machines that can emulate any other machine given its software instructions. Turing later proved that the halting problem, determining if a program will finish running, is undecidable. His proof works by considering a machine M' that determines if another machine M halts on itself as input, leading to circular self-reference that cannot be resolved. Similarly, attempting to solve the halting problem through self-replication results in an endless circular process of self-reproduction, showing the fundamental limits of self-replication and computation.

Variation and Natural Selection | IGCSE BiologyBlessing Ndazie

��

This extensive slide deck provides a detailed exploration of variation and natural selection for IGCSE Biology. It covers key concepts such as genetic and environmental variation, types of variation (continuous and discontinuous), mutation, evolution, and the principles of natural selection. The presentation also explains Darwin’s theory of evolution, adaptation, survival of the fittest, selective breeding, antibiotic resistance in bacteria, and speciation. With illustrative diagrams, real-life examples, and exam-style questions, this resource is ideal for IGCSE students, teachers, and independent learners preparing for exams.

Coordination and Response: The Nervous System | IGCSE BiologyBlessing Ndazie

��

This comprehensive IGCSE Biology presentation explains the nervous system, focusing on how the body coordinates and responds to stimuli. Learn about the central and peripheral nervous systems, reflex actions, neurons, synapses, and the role of neurotransmitters. Understand the differences between voluntary and involuntary responses and how the nervous system interacts with other body systems. Ideal for Cambridge IGCSE students preparing for exams!

QUIZ 1 in SCIENCE GRADE 10 QUARTER 3 BIOLOGYtbalagbis5

��

GALILEO'S OBSERVATION ni Karlo Mariano.pptxejrguillermo

��

Leafcurl viral disease presentation.pptxMir Ali M

��

ARepeatingFastRadioBurstSourceinaLow-luminosityDwarfGalaxySérgio Sacani

��

Wepresent the localizationandhostgalaxyofFRB20190208A, arepeatingsourceof fast radiobursts (FRBs) discoveredusingCHIME/FRB.Aspartof thePinpointingREpeatingChImeSourceswithEVNdishesrepeater localizationprogramon theEuropeanVLBINetwork (EVN),wemonitoredFRB20190208Afor 65.6hr at ∼1.4GHzanddetectedasingleburst,whichledtoitsverylongbaselineinterferometrylocalizationwith260mas uncertainty(2σ).Follow-upopticalobservationswiththeMMTObservatory(i25.7mag(AB))foundnovisible hostattheFRBposition.SubsequentdeeperobservationswiththeGranTelescopioCanarias,however,revealedan extremelyfaintgalaxy(r=27.32±0.16mag),verylikely(99.95%)associatedwithFRB20190208A.Giventhe dispersionmeasureoftheFRB(∼580pccm−3),eventhemostconservativeredshiftestimate( ~ z 0.83 max )implies TheAstrophysicalJournalLetters,977:L4(17pp),2024December10 https://doi.org/10.3847/2041-8213/ad8ce1 ©2024.TheAuthor(s).PublishedbytheAmericanAstronomicalSociety. 30BantingFellow. 31McGillSpaceInstituteFellow. 32 FRQNTPostdoctoralFellow. Originalcontent fromthisworkmaybeusedunder theterms of theCreativeCommonsAttribution4.0licence.Anyfurther distributionofthisworkmustmaintainattributiontotheauthor(s)andthetitle of thework, journalcitationandDOI. 1The Astrophysical Journal Letters, 977:L4 (17pp), 2024 December 10 Hewitt et al. that this is the lowest-luminosity FRB host to date (108 Le), even less luminous than the dwarf host of FRB20121102A. We investigate how localization precision and the depth of optical imaging affect host association and discuss the implications of such a low-luminosity dwarf galaxy. Unlike the other repeaters with low-luminosity hosts, FRB 20190208A has a modest Faraday rotation measure of a few tens of rad m−2, and EVN plus Very Large Array observations reveal no associated compact persistent radio source. We also monitored FRB20190208A for 40.4hr over 2yr as part of the Extragalactic Coherent Light from Astrophysical Transients repeating FRB monitoring campaign on the Nançay Radio Telescope and detected one burst. Our results demonstrate that, in some cases, the robust association of an FRB with a host galaxy will require both high localization precision and deep optical follow-up. Unified Astronomy Thesaurus concepts: Radio bursts (1339); Radio transient sources (2008); Very long baseline interferometry (1769); Dwarf galaxies (416)

Seminario- biología molecular. DiapositivasIsabelaRestrepo10

��

Telescope equatorial mount polar alignment quick reference guidebartf25

��

The Solar System’s passage through the Radcliffe wave during the middle MioceneSérgio Sacani

��

As the Solar System orbits the Milky Way, it encounters various Galactic environments, including dense regions of the interstellar medium (ISM). These encounters can compress the heliosphere, exposing parts of the Solar System to the ISM, while also increasing the influx of interstellar dust into the Solar System and Earth’s atmosphere. The discovery of new Galactic structures, such as the Radcliffe wave, raises the question of whether the Sun has encountered any of them. Aims. The present study investigates the potential passage of the Solar System through the Radcliffe wave gas structure over the past 30 million years (Myr). Methods. We used a sample of 56 high-quality, young (≤30 Myr) open clusters associated with a region of interest of the Radcliffe wave to trace its motion back and investigate a potential crossing with the Solar System’s past orbit. Results. We find that the Solar System’s trajectory intersected the Radcliffe wave in the Orion region. We have constrained the timing of this event to between 18.2 and 11.5 Myr ago, with the closest approach occurring between 14.8 and 12.4 Myr ago. Notably, this period coincides with the Middle Miocene climate transition on Earth, providing an interdisciplinary link with paleoclimatology. The potential impact of the crossing of the Radcliffe wave on the climate on Earth is estimated. This crossing could also lead to anomalies in radionuclide abundances, which is an important research topic in the field of geology and nuclear astrophysics.

More Related Content

More from Hiroki Sayama (13)

How to Make Things EvolveHiroki Sayama

��

Review of linear algebraHiroki Sayama

��

What an ALifer Has Been Doing About COVID-19Hiroki Sayama

��

Self-organization of society: fragmentation, disagreement, and how to overcom...Hiroki Sayama

��

Enhanced ability of information gathering may intensify disagreement among gr...Hiroki Sayama

��

Complexity Explained: A brief intro to complex systemsHiroki Sayama

��

Graph product representation of organism-environment couplings in evolutionHiroki Sayama

��

Suppleness and Open-Endedness for Social SustainabilityHiroki Sayama

��

Adaptive network models of socio-cultural dynamicsHiroki Sayama

��

Effects of Organizational Network Structure and Task-Related Diversity on Col...Hiroki Sayama

��

How to survive as an interdisciplinary beingHiroki Sayama

��

Formulating Evolutionary Dynamics of Organism-Environment Couplings Using Gra...Hiroki Sayama

��

Self-Replication and the Halting ProblemHiroki Sayama

��

How to Make Things EvolveHiroki Sayama

��

Review of linear algebraHiroki Sayama

��

What an ALifer Has Been Doing About COVID-19Hiroki Sayama

��

Self-organization of society: fragmentation, disagreement, and how to overcom...Hiroki Sayama

��

Enhanced ability of information gathering may intensify disagreement among gr...Hiroki Sayama

��

Complexity Explained: A brief intro to complex systemsHiroki Sayama

��

Graph product representation of organism-environment couplings in evolutionHiroki Sayama

��

Suppleness and Open-Endedness for Social SustainabilityHiroki Sayama

��

Adaptive network models of socio-cultural dynamicsHiroki Sayama

��

Effects of Organizational Network Structure and Task-Related Diversity on Col...Hiroki Sayama

��

How to survive as an interdisciplinary beingHiroki Sayama

��

Formulating Evolutionary Dynamics of Organism-Environment Couplings Using Gra...Hiroki Sayama

��

Self-Replication and the Halting ProblemHiroki Sayama

��

Recently uploaded (20)

Variation and Natural Selection | IGCSE BiologyBlessing Ndazie

��

Coordination and Response: The Nervous System | IGCSE BiologyBlessing Ndazie

��

QUIZ 1 in SCIENCE GRADE 10 QUARTER 3 BIOLOGYtbalagbis5

��

GALILEO'S OBSERVATION ni Karlo Mariano.pptxejrguillermo

��

Leafcurl viral disease presentation.pptxMir Ali M

��

ARepeatingFastRadioBurstSourceinaLow-luminosityDwarfGalaxySérgio Sacani

��

Seminario- biología molecular. DiapositivasIsabelaRestrepo10

��

Telescope equatorial mount polar alignment quick reference guidebartf25

��

The Solar System’s passage through the Radcliffe wave during the middle MioceneSérgio Sacani

��

The Arctic through the lens of data visualizationZachary Labe

��

Cell Structure & Function | Cambridge IGCSE BiologyBlessing Ndazie

��

This IGCSE Biology presentation provides a detailed look at cell structure and function, covering the differences between animal and plant cells, the roles of organelles (nucleus, mitochondria, ribosomes, etc.), specialized cells, and levels of organization. Learn about diffusion, osmosis, and active transport in cells, with clear diagrams and explanations to support exam preparation. A must-have resource for Cambridge IGCSE students!

(Journal Club) - DNA replication and repair kinetics of Alu, LINE‑1 and satel...David Podorefsky, PhD

��

Investigational New drug application processonepalyer4

��

first law of thermodynamics class 12(chemistry) final.pdfismitguragain527

��

2025-03-03-Data-related-Ethics Issues in Technologies for Professional Learni...Graz University of Technology & Know-Center

��

How could modern LA research address data-related ethics issues in informal and situated professional learning? I will identify in this talk three relevant insights based on field studies around workplace LA interventions: Firstly, in informal and situated learning, data isn’t just about the learners. Secondly, the affordances of manual and automatic data tracking for learning are very different, with manual tracking allowing a high degree of learner control over data. Thirdly, learning is not necessarily a shared goal in workplaces. These can be translated into seeing a potential for systems endowed with sufficient natural-language-processing capability (now seemingly at our fingertips with LLMs), and socio-technical design and scenario-based data collection analysis as design and research methods.

(Journal Club) - Understanding tumor ecosystems by single-cell sequencing: pr...David Podorefsky, PhD

��

Introduction to Science form 1 students part iiAlejiehyde

��

Direct Gene Transfer Techniques for Developing Transgenic PlantsKuldeep Gauliya

��

Propagation of electromagnetic waves in free space.pptxkanmanivarsha

��

(Journal Club) - Integration of multiple lineage measurements from the same c...David Podorefsky, PhD

��

Variation and Natural Selection | IGCSE BiologyBlessing Ndazie

��

Coordination and Response: The Nervous System | IGCSE BiologyBlessing Ndazie

��

QUIZ 1 in SCIENCE GRADE 10 QUARTER 3 BIOLOGYtbalagbis5

��

GALILEO'S OBSERVATION ni Karlo Mariano.pptxejrguillermo

��

Leafcurl viral disease presentation.pptxMir Ali M

��

ARepeatingFastRadioBurstSourceinaLow-luminosityDwarfGalaxySérgio Sacani

��

Seminario- biología molecular. DiapositivasIsabelaRestrepo10

��

Telescope equatorial mount polar alignment quick reference guidebartf25

��

The Solar System’s passage through the Radcliffe wave during the middle MioceneSérgio Sacani

��

The Arctic through the lens of data visualizationZachary Labe

��

Cell Structure & Function | Cambridge IGCSE BiologyBlessing Ndazie

��

(Journal Club) - DNA replication and repair kinetics of Alu, LINE‑1 and satel...David Podorefsky, PhD

��

Investigational New drug application processonepalyer4

��

first law of thermodynamics class 12(chemistry) final.pdfismitguragain527

��

2025-03-03-Data-related-Ethics Issues in Technologies for Professional Learni...Graz University of Technology & Know-Center

��

(Journal Club) - Understanding tumor ecosystems by single-cell sequencing: pr...David Podorefsky, PhD

��

Introduction to Science form 1 students part iiAlejiehyde

��

Direct Gene Transfer Techniques for Developing Transgenic PlantsKuldeep Gauliya

��

Propagation of electromagnetic waves in free space.pptxkanmanivarsha

��

(Journal Club) - Integration of multiple lineage measurements from the same c...David Podorefsky, PhD

��

Artificial Creativity of Evolutionary Swarm Systems

1. Artificial Creativity of Evolutionary Swarm Systems Hiroki Sayama Center for Collective Dynamics of Complex Systems Binghamton University, State University of New York sayama@binghamton.edu

2. https://www.oreilly.com/ideas/open-endedness- the-last-grand-challenge-youve-never-heard-of 2

3. Swarm Chemistry http://bingweb.binghamton.edu/~sayama/SwarmChemistry/ 3

4. i • Particles in a continuous open 2-D space • Kinetic interactions with local neighbors • No capability to distinguish different types Model Assumptions 4

5. Kinetic Parameters (Assigned to each particle individually) 5

6. i Cohesion Alignment Separation 97 * (226.76, 3.11, 9.61, 0.15, 0.88, 43.35, 0.44, 1.0 ) 38 * ( 57.47, 9.99, 35.18, 0.15, 0.37, 30.96, 0.05, 0.31) 56 * ( 15.25, 13.58, 3.82, 0.3, 0.8, 39.51, 0.43, 0.65) 31 * (113.21, 18.25, 38.21, 0.62, 0.46, 15.78, 0.49, 0.61) Recipe 6

8. Recipe Competition Between Active Particles Competition between active particles 97 * (226.76, 3.11, 9.61, 0.15, 0.88, 43.35, 0.44, 1.0) 38 * (57.47, 9.99, 35.18, 0.15, 0.37, 30.96, 0.05, 0.31) 56 * (15.25, 13.58, 3.82, 0.3, 0.8, 39.51, 0.43, 0.65) 31 * (113.21, 18.25, 38.21, 0.62, 0.46, 15.78, 0.49, 0.61) 67 * (216.35, 11.75, 7.7, 0.83, 0.97, 97.31, 0.02, 0.38) 29 * (254.64, 7.28, 7.0, 0.95, 0.11, 22.41, 0.43, 0.31) 13 * (105.4, 3.55, 5.24, 0.34, 0.18, 23.53, 0.39, 0.24) competition function winner: 8

9. 97 * (226.76, 3.11, 9.61, 0.15, 0.88, 43.35, 0.44, 1.0) 38 * (57.47, 9.99, 35.18, 0.15, 0.37, 30.96, 0.05, 0.31) 56 * (15.25, 13.58, 3.82, 0.3, 0.8, 39.51, 0.43, 0.65) 31 * (113.21, 18.25, 38.21, 0.62, 0.46, 15.78, 0.49, 0.61) Mutations Recipe transmission & mutation 75 * (216.35, 11.75, 7.7, 0.83, 0.97, 97.31, 0.02, 0.38) 29 * (254.64, 7.28, 7.0, 0.95, 0.11, 28.56, 0.43, 0.31) 13 * (105.4, 3.55, 5.24, 0.34, 0.18, 23.53, 0.39, 0.24) 9 67 * (216.35, 11.75, 7.7, 0.83, 0.97, 97.31, 0.02, 0.38) 29 * (254.64, 7.28, 7.0, 0.95, 0.11, 22.41, 0.43, 0.31) 13 * (105.4, 3.55, 5.24, 0.34, 0.18, 23.53, 0.39, 0.24)

10. Sayama, IEEE ALIFE (2011) Sayama & Wong, ECAL (2011) Is This Really Creative?

11. Simulate It Much Longer Detect Objects Automatically

12. Automated Object Harvesting

14. Environmental Perturbations • Competition function switched from “majority-relative” to either “faster” or “slower” for T steps in every 2000 steps in either half of the space T = 50 (short, moderate) T = 500 (long, severe)

15. Detailed Object Tracking (Object Size) With moderate environmental perturbations Objects tend to get bigger over time

16. Detailed Object Tracking (Object Size) With moderate environmental perturbations With severe environmental perturbations But it also depends on the severity of perturbations

17. Detailed Object Tracking (Color Diversity) With moderate environmental perturbations With severe environmental perturbations Severe perturbations may increase color entropy of objects

18. Results https://youtu.be/BpN-DE3o6u8

19. Evolved Under Moderate Perturbations

20. Evolved Under Severe Perturbations

21. Conclusions Evolutionary swarm chemistry can produce patterns with no global fitness evaluation The “bottom-up” approach offers a unique path to machine creativity Automated object harvesting has captured a large number of patterns

22. Thank You @hirokisayama

�ݺ�ߣ

Artificial Creativity of Evolutionary Swarm Systems

Recommended

More Related Content

More from Hiroki Sayama (13)

Recently uploaded (20)

Artificial Creativity of Evolutionary Swarm Systems