CT002-3-2 AI Methods

Swarm Intelligence, technique

and application-II
 How To Think: Swarm
Intelligence Observation

Create Extract
Observation Model Metaheuristic
Model Metaheuristic

Build
Test
Refine

Simulation Algorithm

Swarm intelligence (SI) as defined by Bona beau, Dorigo

and Theraulaz is "any attempt to design algorithms or
distributed problem-solving devices inspired by the
collective behavior of social insect colonies and other
animal societies"
CT002-3.5-2 AI Methods Machine Learning
 metaheuristic

• higher-level procedure or heuristic

designed to find, generate, or select a
heuristic (partial search algorithm) that
may provide a sufficiently good solution to
an optimization problem, especially with
incomplete or imperfect information

CT002-3.5-2 AI Methods Machine Learning

 Modeling

 Reynolds created a "boid" model in 1986 - A distributed

behavioral model, to simulate the motion of a flock of birds.

 Each boid is an independent actor that navigates on its

own perception of the dynamic environment.

Four Rules of Boid Model

Avoidance rule
Copy rule
Center rule
View rule

CT002-3.5-2 AI Methods Machine Learning

 What are the principal mechanisms of
natural organization?
Self-organization

‘Self-organization is a set of dynamical mechanisms

whereby structures appear at the global level of a system
from interactions of its lower-level components.’
(Bonabeau et al, in Swarm Intelligence, 1999)

CT002-3.5-2 AI Methods Machine Learning

 • Self-organization : can be defined as a set of dynamical
mechanisms that establish basic rules for interactions between
the components of the system.
• The rules ensure that the interactions are executed on the basis
of purely local information without any relation to the global
pattern.

• Division of Labor: In swarm behavior different tasks are

performed simultaneously by specialized individuals which is
referred to as division of labor. It enables swarm to respond to
changed conditions in the search space.

CT002-3.5-2 AI Methods Machine Learning

 The four bases of self-organization

a)Positive feedback (amplification)

b)Negative feedback (for counter-balance and stabilization)
c)Amplification of fluctuations (randomness, errors, random walks)
d)Multiple interactions

CT002-3.5-2 AI Methods Machine Learning

 Self-organization
• Positive feedback: As the nectar amount of food sources
increases, the number of onlookers visiting them increases,
too.

• Negative feedback: The exploitation process of poor food

sources is stopped by bees.

• Fluctuations: The scouts carry out a random search process

for discovering new food sources.

• Multiple interactions: Bees share their information about

food sources with their nest mates on the dance area.
CT002-3.5-2 AI Methods Machine Learning
 Behavior of Honey Bee Swarm
Three essential components of forage selection:

• Food Sources: The value of a food source depends on many factors such as its
proximity to the nest, its richness or concentration of its energy, and the ease of
extracting this energy.

• Employed Foragers: They are associated with a particular food source which
they are currently exploiting or are “employed” at. They carry with them
information about this particular source, its distance and direction from the nest,
the profitability of the source and share this information with a certain probability.

• Unemployed Foragers: They are continually at look out for a food source to
exploit. There are two types of unemployed foragers: scouts, searching the
environment surrounding the nest for new food sources and onlookers waiting in
the nest and establishing a food source through the information shared by
employed foragers.

CT002-3.5-2 AI Methods Machine Learning

 Foraging

CT002-3.5-2 AI Methods Machine Learning

 Exchange of Information among bees

• The exchange of information among bees is the most

important occurrence in the formation of collective
knowledge.

• The most important part of the hive with respect to

exchanging information is the dancing area

• Communication among bees related to the quality of

food sources takes place in the dancing area.

• This dance is called a Waggle dance.

CT002-3.5-2 AI Methods Machine Learning
 • Employed foragers share their information with a probability
proportional to the profitability of the food source, and the
sharing of this information through waggle dancing is longer in
duration.

• An onlooker on the dance floor, probably she can watch

numerous dances and decides to employ herself at the most
profitable source.

• There is a greater probability of onlookers choosing more

profitable sources since more information is circulated about the
more profitable sources.

CT002-3.5-2 AI Methods Machine Learning

CT002-3.5-2 AI Methods Machine Learning
 Bee Waggle Dance

CT002-3.5-2 AI Methods Machine Learning

 Artificial Bee Colony Algorithm

• Simulates behavior of real bees for solving multidimensional and

multimodal optimisation problems.

• The colony of artificial bees consists of three groups of bees:

employed bees, onlookers and scouts.

• The first half of the colony consists of the employed artificial bees
and the second half includes the onlookers.

• The number of employed bees is equal to the number of food

sources around the hive.

• The employed bee whose food source has been exhausted by the
bees becomes a scout.
CT002-3.5-2 AI Methods Machine Learning
 ABC Algorithm

CT002-3.5-2 AI Methods Machine Learning

 Explanation

• Each cycle of search consists of three steps: moving the

employed and onlooker bees onto the food sources and
calculating their nectar amounts; and determining the scout
bees and directing them onto possible food sources.

• A food source position represents a possible solution to the

problem to be optimized.

• The amount of nectar of a food source corresponds to the

quality of the solution

• Onlookers are placed on the food sources by using a

probability based selection process.
CT002-3.5-2 AI Methods Machine Learning
 • As the nectar amount of a food source increases, the
probability value with which the food source is preferred by
onlookers increases, too.
• The scouts are characterized by low search costs and a low
average in food source quality. One bee is selected as the scout
bee.
• The selection is controlled by a control parameter called
"limit".
• If a solution representing a food source is not improved by a
predetermined number of trials, then that food source is
abandoned and the employed bee is converted to a scout.

CT002-3.5-2 AI Methods Machine Learning

 Ant foraging
Cooperative search by pheromone trails

CT002-3.5-2 AI Methods Machine Learning

 Characteristics of self-organized
systems

 Structure emerging from a homogeneous startup state.

 Multistability - coexistence of many stable states.
 State transitions with a dramatic change of the system
behaviour.

CT002-3.5-2 AI Methods Machine Learning

 Self-organization in a termite simulation

CT002-3.5-2 AI Methods Machine Learning

 Stigmergy

Stigmergy: stigma (sting) + ergon (work)

= ‘stimulation by work’

Characteristics of stigmergy

 Indirect agent interaction modification of the environment

 Environmental modification serves as external memory
 Work can be continued by any individual
 The same, simple, behavioural rules can create different
designs
 According to the environmental state

CT002-3.5-2 AI Methods Machine Learning

 Stigmergy

• Stigmergy is a mechanism of indirect

coordination between agents or actions.
The principle is that the trace left in the
environment by an action stimulates the
performance of a next action, by the same
or a different agent

CT002-3.5-2 AI Methods Machine Learning

 Stigmergy

CT002-3.5-2 AI Methods Machine Learning

 From Ants to Algorithms

• Swarm intelligence information

allows us to address modeling via:
– Problem solving
– Algorithms
– Real world applications

CT002-3.5-2 AI Methods Machine Learning

 Modeling

• Observe Phenomenon

• Create a biologically motivated

model

• Explore model without constraints

CT002-3.5-2 AI Methods Machine Learning

 Modeling...

• Creates a simplified picture of reality

• Observable relevant quantities

become variables of the model

• Other (hidden) variables build

connections

CT002-3.5-2 AI Methods Machine Learning

 A Good Model has...

• Parsimony (simplicity)

• Coherence

• Refutability

• Parameter values correspond to

values of their natural counterparts

CT002-3.5-2 AI Methods Machine Learning

 Travelling Salesperson
Problem
Initialize
Loop /* at this level each loop is called an iteration */
Each ant is positioned on a starting node
Loop /* at this level each loop is called a step */
Each ant applies a state transition rule to incrementally
build a solution and a local pheromone updating rule
Until all ants have built a complete solution
A global pheromone updating rule is applied
Until End_condition

M. Dorigo, L. M. Gambardella : ftp://iridia.ulb.ac.be/pub/mdorigo/journals/IJ.16-TEC97.US.pdf

Ant Colony System: A Cooperative Learning Approach to the Traveling Salesman Problem

CT002-3.5-2 AI Methods Machine Learning

 Traveling Sales Ants

CT002-3.5-2 AI Methods Machine Learning

 Questions & Answers

CT002-3.5-2 AI Methods Machine Learning