A special feature of IEEE CEC is the Tutorial programme which enables all delegates
to increase their knowledge of evolutionary computation from leading expects in
the field. Topics are offered at introductory, intermediate and advanced
levels in a range of subjects ranging from the fundamentals to specialist
subjects. Tutorials last 2 hours and will take place on May 18 2009, the day
before the main conference begins. Attendance at Tutorial sessions is included
in the conference registration fee and all tutorial slides will be available on
CD as part of the conference registration pack.
Proposals for Tutorial sessions are welcome. Interested researchers are invited
to contact the Tutorial Chair, Steve Smith, with a proposal that should include
the title, outline content (and if possible, some sample slides), expected
enrolment and short one-page CV, by email at
sls@ohm.york.ac.uk. The deadline for Tutorial proposals is
1st December 2008 and notification of acceptance will be made by 16th January 2009.
Kalyanmoy Deb, Indian Institute of Technology Kanpur, India
Evolutionary Computation: A Unified Approach
Presenter: Kenneth De Jong
Institution: Department of Computer Science, George Mason University
The field of Evolutionary Computation has experienced tremendous growth over
the past 20 years, resulting in a wide variety of evolutionary algorithms and
applications. The result poses an interesting dilemma for many practitioners
in the sense that, with such a wide variety of algorithms and approaches, it is
often hard to se the relationships between them, assess strengths and
weaknesses, and make good choices for new application areas.
This tutorial is intended to give an overview of a general EC framework that
can help compare and contrast approaches, encourages crossbreeding, and
facilitates intelligent design choices. The use of this framework is then
illustrated by showing how traditional EAs can be compared and contrasted with
it, and how new EAs can be effectively designed using it.
Finally, the framework is used to identify some important open issues that need
further research.
Genetic Programming Practice and Theory
Presenter: Riccardo Poli
Institution: Department of Computing and Electonic Systems, University of Essex
Genetic programming (GP) is an evolutionary technique for getting
computers to automatically solve problems without having to tell them
explicitly how to do it (Koza, 1992). Since its inception genetic
programming has been used to solve many practical problems including
producing a number of human competitive results and even patentable
new inventions (Poli et al, 2008).
This tutorial includes two parts. In the first part I will introduce
the basics of GP practice, briefly explaining GP representations,
operators and search algorithm, and showing examples of real
runs. This will mainly be based on (Koza, 1992) and (Poli et al,
2008). In the second part of the tutorial, I will then concentrate on
explaining how and why GP works. This will done by first
characterising GP's search space (the space of all possible programs)
and then by explaining the way in which GP explores such a space. This
will be based mainly on (Langdon and Poli, 2002) and (Poli et al,
2008).
Despite its technical contents, the tutorial will require limited
mathematical background.
J.R. Koza, Genetic Programming: On the Programming of Computers by
Means of Natural Selection, MIT Press, 1992.
W.B. Langdon and R. Poli, Foundations of Genetic Programming,
Springer, 2002.
R. Poli, W.B. Langdon and N.F. McPhee, A Field Guide to Genetic
Programming, Lulu.com, 2008 (freely available from the Internet).
Principled Approaches to tuning EA parameters
Presenter: A.E. Eiben
Institution: Vrije Universiteit Amsterdam
Finding appropriate parameter values for evolutionary algorithms (EA) is one
of the persisting grand challenges of the evolutionary computing (EC) field.
On the one hand, all EC researchers and practicioners acknowledge that good
parameter values are essential for good EA performance. On the other hand,
even after 30 years of EC research there is very little known about the effect
of EA parameters on EA performance. Users mostly rely on conventions (mutation
rate should be low), ad hoc choices (why not use uniform crossover), and
experimental comparisons on a limited scale (testing combinations of three
different crossover rates and three different mutation rates). Hence, there is
a striking gap between the widely acknowledged importance of good parameter
values and the widely exhibited ignorance concerning principled approaches to
tune EA parameters.
The aims of this tutorial are threefold: creating awareness, providing
guidelines, and presenting a vision for future development. As for the
awareness, we will discuss the matter of EA parameters, catagorize different
ways of setting them, and discuss the most important related issues, inlcuding
performance measures and test functions. In the guidelines section we review
existing algorithmic approaches to parameter tuning. We will discuss sweep
methods, search methods, and combined methods, positioning them on a feature
map and present (comparative) results on their usefulness. In the last part,
we take a future-oriented attitude and identify research areas with high
relevance and potential impact.
Recent Challenges to Evolutionary Multi-Criterion Optimization (EMO)
Presenter: Kalyanmoy Deb
Institution: Indian Institute of Technology Kanpur, India
Many real-world search and optimization problems involve multiple objectives
which are conflicting to each other. These problems give rise to a set of
Pareto-optimal solutions which must be found and a decision-making task must be
used to choose a particular preferred solution. Since 1993, Evolutionary
algorithms (EAs) have been amply demonstrated to find a well-distributed set of
near Pareto-optimal solutions in many problems. In this tutorial, we shall
discuss a number of such evolutionary multi-objective optimization (EMO)
techniques, assess the current state-of-the-art techniques, and highlight a
number of recent challenges which must be paid more attention. Some of these
challenges include:
Inclusion of multi-criterion decision-making aides within EMO framework so
as to achieve both optimization and decision-making tasks to find a single
preferred solution.
Handling a large number of objectives (such as 10 or more) which often arise in
real-world scenarios.
Handling practical complexities using EMO, such as uncertainties in decision
variables and parameters, reliability issues, computationally demanding
solution evaluation, non-linear constraints etc.
Handling dynamic multi-objective optimization problems in which objectives and
constraints change with the progress of an EMO simulation
Use of EMO principles to other problem solving tasks
Use of EMO methodology for knowledge extraction in real-world problems
This tutorial is aimed for both novices and users of EMO. Those without any
knowledge in EMO will have adequate ideas of the procedures and their
importance in computing and problem-solving tasks. Those who have been
practicing EMO will also have enough ideas and materials for future research,
know state-of-the-art results and techniques, and make a comparative evaluation
of their research.
