Professional Documents
Culture Documents
Swarm Intelligence
Swarm Intelligence
Swarm Intelligence
SWARM INTELLIGENCE
A Short Introduction
http://link.hkilter.com/swarm
Keynote Live
Citation
Series in Biologically Inspired Computation 3
İlter, H. K. 2021. A short introduction to swarm intelligence. figshare.
Presentation. https://doi.org/10.6084/m9.figshare.16910104
Eukaryota
Archaea
Source: https://en.wikipedia.org/wiki/File:Tree_of_life_SVG.svg
INTELLIGENCE
Measurements
Encephalization quotient (EQ) Currently the best predictor for intelligence across all
animals is forebrain neuron count*.
Snell's allometry equation: E = CS r * Herculano-Houzel, S. 2017. Numbers of neurons as biological correlates of cognitive
capability. Current Opinion in Behavioral Sciences, 16: 1–7.
E, weight of the brain
C, cephalization factor - EQ
r, exponential constant
C = ES 2/3
Number of neurons
Neurons are the cells that transmit information in an
animal's nervous system so that it can sense stimuli from
its environment and behave accordingly.
INTELLIGENCE
Natural Intelligence
Simple representation
Name Plants
Domain: Eukaryota
(unranked): Diaphoretickes
Scienti c classi cation
(unranked): Archaeplastida
Kingdom: Plantae
Brain-to-body mass ratio 1:7 Brain-to-body mass ratio* 1:7 Brain-to-body mass ratio 1:12—
Number of neurons 105—106 (largest among the invertebrates) 1:2789
Number of neurons 5×108 (most Number of neurons 4×106—2.5×1011
Eg. Ants, cockroaches, spiders complex of all invertebrates)
Eg. Mammals, birds, reptiles, fish
• Ant colony optimization Eg. Octopus, squids, cuttlefish
• Artificial bee colony algorithm • Boids, simulation
• Particle swarm optimization • Neural networks • Bat algorithm, metaheuristic
• Clustering • Learning models optimization
• Cat swarm optimization
* Shigeno, S., Andrews, P., Ponte, G., & Fiorito,
G. (2018). Cephalopod Brains: An Overview of
Current Knowledge to Facilitate Comparison
With Vertebrates. Frontiers in physiology, 9,
952. https://doi.org/10.3389/fphys.2018.00952
INTELLIGENCE
Intelligence in Nature
Primates H. sapiens
Kingdom: Animalia Kingdom: Animalia
Phylum: Chordata Phylum: Chordata
Class: Mammalia Class: Mammalia
Clade: Pan-Primates Order: Primates
Order: Primates Suborder: Haplorhini
Infraorder: Simiiformes
Family: Hominidae
Subfamily: Homininae
Tribe: Hominini
Genus: Homo
Species: H. sapiens
Bernard Bolzano
Semantics
Antiquity
René Descartes
Bodies are complex
machines
Kurt Gödel
Theoretical computer IBM
OpenAI
science Deep Blue
GPT-3
IBM
Watson
Future
• Thinking humanly
• Thinking rationally
• Acting humanly
• Acting rationally
fi
fi
ARTIFICIAL INTELLIGENCE
De ning Arti cial Intelligence
Thinking Humanly The Cognitive Modeling Approach - Newell and Simon (1961)
The exciting new effort to make computers think ... The interdisciplinary field of cognitive science brings
machines with minds, in the full and literal sense. together computer models from AI and experimental
— Haugeland, 1985 techniques from psychology to construct precise and
John Haugeland. 1985. Artificial intelligence: The very idea. Bradford books. The MIT testable theories of the human mind.
Press, Cambridge, Mass., and London.
The art of creating machines that perform functions that Turing Test
require intelligence when performed by people. Natural language processing to enable it to communicate
— Kurzweil, 1990 successfully in English,
Kurzweil, R., Jaroch, D. 1990. The Age of Intelligent Machines. Cambridge, Mass., MIT Knowledge representation to store what it knows or
Press.
hears,
Automated reasoning to use the stored information to
The study of how to make computers do things at which, answer questions and to draw new conclusions,
at the moment, people are better. Machine learning to adapt to new circumstances and to
— Rich and Knight, 1991 detect and extrapolate patterns.
Rich, E., Knight, K. 1991. Arti icial Intelligence. New York, N.Y: McGraw-Hill, Inc.
Computational [i]ntelligence is the study of the design of Computer agents are expected to do more: operate
intelligent agents. autonomously, perceive their environment, persist over a
— Poole et al., 1998 prolonged time period, adapt to change, and create and
Poole, D., Mackworth, A. K., Goebel, R. G. 1998. Computational Intelligence: A logical pursue goals. A rational agent is one that acts so as to
approach. New York: Oxford University Press.
achieve the best outcome or, when there is uncertainty,
the best expected outcome.
AI ... is concerned with intelligent behavior in artifacts.
— Nilsson, 1998
Nilsson, N. J. 1998. Artificial Intelligence: A new synthesis. San Francisco, Calif:
Morgan Kaufmann Publishers.
fi
fi
ARTIFICIAL INTELLIGENCE
Google Duplex
Making an appointment
Source: https://www.youtube.com/watch?v=JvbHu_bVa_g
ARTIFICIAL INTELLIGENCE
De ning Arti cial Intelligence
AI generated art
Source: https://deepart.io/img/0SQJ7PBH
Strong AI Weak AI
Artificial General Intelligence (AGI) is the hypothetical It is any program that is designed to solve exactly one
ability of an intelligent agent to understand or learn any problem.
intellectual task that a human being can.
Academic sources reserve weak AI for programs that do
Academic sources reserve the term strong AI for computer not experience consciousness or do not have a mind in the
programs that experience sentience or consciousness. same sense people do.
fi
ARTIFICIAL INTELLIGENCE
Types of Arti cial Intelligence
Source: https://commons.wikimedia.org/wiki/
File:Bongard_problem_convex_polygons.svg
https://upload.wikimedia.org/wikipedia/commons/thumb/a/a0/P_np_np-
complete_np-hard.svg/600px-P_np_np-complete_np-hard.svg.png
fi
ARTIFICIAL INTELLIGENCE
Goals and Tools
Goals Tools
• Reasoning, problem solving • Search and optimization
• Knowledge representation Search algorithm, Mathematical optimization and
Evolutionary computation
• Planning
• Learning • Logic
Logic programming and Automated reasoning
• Natural language processing
• Probabilistic methods for uncertain reasoning
• Perception
Bayesian network, Hidden Markov model, Kalman
• Motion and manipulation
filter, Decision theory and Utility theory
• Social intelligence
• Classifiers and statistical learning methods
• General intelligence Classifier (mathematics), Statistical classification and
Machine learning
• Neural networks
Artificial neural network and Connectionism
• Control theory
• Languages
NATURAL COMPUTING
De ning Natural Computing
A definition
Natural computing is a terminology introduced to
encompass three classes of methods:
1. those that take inspiration from nature for the
development of novel problem-solving techniques;
2. those that are based on the use of computers to
synthesize natural phenomena; and
3. those that employ natural materials to compute.
fi
NATURAL COMPUTING
Types of Natural Computing
A definition Examples
Swarm behavior, or swarming, is a collective behavior
exhibited by entities, particularly animals, of similar size Bird flocks
which aggregate together, perhaps milling about the same Fish schools
spot or perhaps moving en masse or migrating in some
Insect swarms
direction.
Bacteria swarms
Bouffanais, R.2016. Design and Control of Swarm Dynamics. Springer Briefs in
Complexity (First ed.). Springer. Quadruped herds
Algal blooms - phytoplankton (algae)
Another definition
From a more abstract point of view, swarm behavior is
the collective motion of a large number of self-propelled
entities.
O'Loan, E. 1998. Alternating steady state in one-dimensional flocking. Journal of Physics
A: Mathematical and General. 32 (8): L99–L105.
fi
SWARM BEHAVIOUR
Understand the Behavior, Biologically
Zone of attraction
The simplest mathematical models of Move towards the
neighbor
animal swarms generally represent
individual animals as following three
rules: Zone of alignment
Align direction of
• Move in the same direction as their motion
neighbors
Zone of repulsion
• Remain close to their neighbors Avoid collision
• Avoid collisions with their neighbors
Separation: steer to avoid crowding local Alignment: steer towards the average Cohesion: steer to move toward the average
flockmates heading of local flockmates position of local flockmates
SWARM INTELLIGENCE
Boids
Source: https://www.youtube.com/watch?v=bqtqltqcQhw
For boids see http://www.red3d.com/cwr/boids/
SWARM INTELLIGENCE
Algorithms and Approaches
Bishop, J.M. (1989). "Stochastic Searching Networks" (PDF). Proc. 1st IEE Conf. on
Artificial Neural Networks. London: 329–331.
Bishop, J.M. & Torr, P., (1992). The Stochastic Search Network. In R. Linggard, D.J.
Myers, C. Nightingale (eds.), Neural Networks for Images, Speech and Natural
Language, pp370–387, New York, Chapman & Hall.
Grech-Cini, H.J. & McKee, G.T. (1993) Locating the Mouth Region in Images of
Human Faces. In P.S.Schenker (Ed.), Proceedings of SPIE – The International Society
for Optical Engineering, Sensor Fusion VI 2059, Massachusetts.
Beattie, P.D. & Bishop, J.M., (1998). Self-Localisation in the 'Senario' Autonomous
Wheelchair. Journal of Intelligent and Robotic Systems 22, pp 255–267, Kluwer
Academic Publishers.
Whitaker, R.M., Hurley, S., (2002). An agent based approach to site selection for
wireless networks. Proc ACM Symposium on Applied Computing (Madrid). 574–577.
SWARM INTELLIGENCE
Algorithms
Colorni, A., Dorigo, M., Maniezzo, V. 1991. Distributed optimization by ant colonies.
Proceedings of the European Conference on Arti icial Life, ECAL’91, 134-142.
Dorigo, M. 1992. Optimization, Learning and Natural Algorithms. PhD thesis, Politecnico
di Milano, Italy.
Source: https://commons.wikimedia.org/wiki/
File:Aco_shortpath.svg
f
SWARM INTELLIGENCE
Algorithms
Pham DT, Ghanbarzadeh A, Koc E, Otri S, Rahim S and Zaidi M. The Bees Algorithm.
Technical Note, Manufacturing Engineering Centre, Cardiff University, UK, 2005.
Pham, D.T., Castellani, M. (2009), The Bees Algorithm – Modelling Foraging
Behaviour to Solve Continuous Optimisation Problems. Proc. ImechE, Part C, 223(12),
2919-2938.
Pham, D.T. and Castellani, M. (2013), Benchmarking and Comparison of Nature-
Inspired Population-Based Con- tinuous Optimisation Algorithms, Soft Computing,
1-33.
SWARM INTELLIGENCE
Algorithms
X. S. Yang, A New Metaheuristic Bat-Inspired Algo- rithm, in: Nature Inspired K.N. Krishnanand and D. Ghose. (2006). Glowworm swarm based optimization
Cooperative Strategies for Optimization (NISCO 2010) (Eds. J. R. Gonzalez et al.), algorithm for multimodal functions with collective robotics applications. Multi- agent
Studies in Computational Intelligence, Springer Berlin, 284, Springer, 65-74 (2010). and Grid Systems, 2(3):209- 222.
K.N. Krishnanand and D. Ghose. (2009). Glowworm swarm optimization for
simultaneous capture of multi- ple local optima of multimodal functions. Swarm Intelli-
gence, 3(2):87- 124.
K.N. Krishnanand and D. Ghose. (2008). Theoretical foundations for rendezvous of
glowworm-inspired agent swarms at multiple locations. Robotics and Auton- omous
Systems, 56(7):549- 569.
SWARM INTELLIGENCE
Algorithms
Buhl, J.; Sumpter, D. J. T.; Couzin, D.; Hale, J. J.; Desp- land, E.; Miller, E. R.; Simpson,
S. J. (2006). “From dis- order to order in marching locusts” (PDF). Science 312 (5778):
1402–1406.
Series in Biologically Inspired Computation 3
SWARM INTELLIGENCE
A Short Introduction