Download The Evolution of Evolutionary Computation

The Evolution of
Evolutionary Computation
Xin Yao
CERCIA, School of Computer Science, University of Birmingham, UK
http://www.cercia.ac.uk
What Is Evolutionary Computation
  It is the study of computational systems
which use ideas and get inspirations
from natural evolution.
  Evolutionary computation (EC)
techniques can be used in optimisation,
learning and creative design.
  EC techniques do not require rich
domain knowledge to use. However,
domain knowledge can be incorporated
into EC techniques.
Characteristics of
Evolutionary Computation
  Flexible:
applicable to different problems
  Robust:
can deal with noise and uncertainty
  Adaptive:
can deal with dynamic environments
  Autonomous:
without human intervention
  Decentralised:
without a central authority
Outline of This Talk
 Heuristic Optimisation
  Data Mining and Machine Learning
Case Study I:
Modelling
Discovering `New’ Physical Laws in Astrophysics
--- Modelling Radial Brightness Distributions in
Elliptical Galaxies
  Empirical laws are widely used in astrophysics.
  However, as the observational data increase,
some of these laws do not seem to describe
the data very well.
  Can we discover new empirical laws that
describe the data better?
Monochromatic (Negative) Images of Galaxies
disk
bulge
A typical elliptical galaxy
A typical spiral galaxy
Current Approach
  Select a functional form in advance
Drawbacks: ad hoc, difficult to determine and may only suit a
smaller number of profiles
  Apply fitting algorithms to find suitable
parameters for the function. Usually adopt
the non-linear reduced c2 minimization
No se puede mostrar la imagen. Puede que su equipo no tenga suficiente memoria para abrir la imagen o que ésta esté dañada. Reinicie el equipo y, a
continuación, abra el archivo de nuevo. Si sigue apareciendo la x roja, puede que tenga que borrar la imagen e insertarla de nuevo.
χ2 = where Iobs(i) is the individual observed profile value, Imodel(i) is the value calculated from the
fitting function, υ is the number of degrees of freedom, and δ is the standard deviation of the
data.
Drawbacks: difficult to set initial values and easily trapped in local minima
Our Evolutionary Approach
(1) Find functional forms using GP (Genetic Programming) :
 
 
A data-driven process without assuming a functional form in
advance
A bottom up process which suits modelling a large number of
galaxy profiles without any prior knowledge of them
(2) Fit parameters in the form found using FEP (Fast
Evolutionary Programming):
 
 
Not sensitive to initial setting values
More likely to find global minima
J. Li, X. Yao, C. Frayn, H. G. Khosroshahi, S. Raychaudhury, ``An Evolutionary Approach to
Modeling Radial Brightness Distributions in Elliptical Galaxies,'' Proc. of the 8th
International Conference on Parallel Problem Solving from Nature (PPSN VIII), Lecture
Notes in Computer Science, Vol. 3242, pp.591-601, Springer, September 2004.
Case Study in Astrophysics =
Real-world Problems?
Yet another mad professor? …
Case Study II: Modelling
Determining Unified Creep Damage Constitutive
Equations in Aluminium Alloy Modelling
  Creep behaviours of different materials are
often described by physically based unified
creep damage constitutive equations.
  Such equations are extremely complex.
  They often contain undecided constants
(parameters).
  Traditional approaches are unable to find good
near optima for these parameters.
  Evolutionary algorithms (EAs) have been shown
to be very effective.
Example Equations
Model with Evolved Parameters by IFEP
Evolutionary Parameter
Calibration and Optimisation
  Classical evolutionary programming
(CEP), fast EP (FEP) and improved
fast EP (IFEP) can be used to find
parameters in a complex and nondifferentiable space.
B. Li, J. Lin and X. Yao, “A novel evolutionary algorithm
for determining unified creep damage constitutive
equations,” International Journal of Mechanical
Sciences, 44 (2002) 987–1002.
Impact
  Have been used by Corus / Tata Corus
since 2001.
Constraint Handling
  Real-world problems have many
constraints, e.g., linear, nonlinear,
equality, inequality, …
An Example
  Stochastic ranking: is a constraint
handling method that can be used
with any evolutionary optimisation
algorithms
 
 
T. P. Runarsson and X. Yao, “Stochastic Ranking for Constrained
Evolutionary Optimization,” IEEE Transactions on Evolutionary
Computation, 4(3):284-294, September 2000.
T. Runarsson and X. Yao, “Search Bias in Constrained
Evolutionary Optimization,” IEEE Transactions on Systems, Man,
and Cybernetics, Part C, 35(2):233-243, May 2005.
Impact
  It’s used so often that people made it a C library
so that everyone can use easily:
  Xinglai Ji 1 and Ying Xu 2, “libSRES: a C library for stochastic
ranking evolution strategy for parameter estimation”
Bioinformatics, 22(1):124-126, 2006.
  1Computational Biology Institute, Oak Ridge National Laboratory Oak
Ridge, TN 37831, USA
2Department of Biochemistry and Molecular Biology and Institute of
Bioinformatics, University of Georgia Athens, GA 30602-7229, USA
  Also in civil, mechanical, electrical and electronic
engineering.
Real World Is Complex
  Real world is complex and changes
all the time.
  E.g., customers make new orders or cancel existing
orders all the time. How can I optimise my
objectives?
Case Study III:
Dynamic Optimisation
Gritter Routing
 
Optimisation Problem:
- 
- 
- 
- 
Multiple trucks, multiple
depots,
different capacities
Routing constraints
Dynamic
H. Handa, L. Chapman and Xin Yao,
``Robust route optimisation for
gritting/salting trucks: A CERCIA
experience,'' IEEE Computational
Intelligence Magazine, 1(1):6-9,
February 2006.
Optimised Routing
Case Study IV:
Multi-objective Optimisation
Patented Multi-objective Design
  Patent:
  X. Yao and T. Schnier, “HARDWARE DESIGN USING
EVOLUTION ALGORITHMS,” European Patent EP1388123.
Held by Ericsson (formerly Marconi).
  Papers:
  T. Schnier, X. Yao and P. Liu, “Digital filter design
using multiple pareto fronts,” Soft Computing, 8(5):
332-343, April 2004.
  S. Salcedo-Sanz, F. Cruz-Rold\'an, C. Heneghan and
X. Yao, “Evolutionary Design of Digital Filters with
Application to Sub-band Coding and Data
Transmission,” IEEE Transactions on Signal
Processing, 55(4):1193-1203, April 2007.
Not Just Hardware Engineering
  K. Praditwong, M. Harman and X. Yao,
“Software Module Clustering as a MultiObjective Search Problem,” IEEE Transactions
on Software Engineering, accepted in August
2009.
  Z. Wang, K. Tang and X. Yao, “Multi-objective
Approaches to Optimal Testing Resource
Allocation in Modular Software Systems,” IEEE
Transactions on Reliability, 59(3):563-575,
September 2010.
Outline
  Adaptive Optimisation
  Data Mining and Machine Learning
Supervised Learning
  Given a set of historical data, we want to
build (learn) the best model that can
predict the future for new input data.
  Challenges:
  Noise
  Concept drift over time
  Multi-objectives (cheap and high-quality)
  …
Links Between EC and Learning
Use the whole population as a
learner:
  X. Yao and Y. Liu, “Making use of population
information in evolutionary artificial neural
networks,” IEEE Trans. on Systems, Man, and
Cybernetics, Part B: Cybernetics, 28(3):417-425,
June 1998.
Case Study V:
Ensemble Learning
Negative Correlation Learning
  Negative Correlation Learning is an
ensemble learning algorithm:
  Paper:
  Y. Liu and X. Yao, ``Ensemble learning via
negative correlation,'' Neural Networks, 12(10):
1399-1404, December 1999.
  Patent:
  Xin Yao, Gavin Brown, Bernhard Sendhoff and
Heiko Wersing, “Exploiting ensemble diversity
for automatic feature extraction,” European
Patent EP1378855. (Held by Honda).
Multi-objective Learning
  Learning with multi-objectives:
 
H. Chen and X. Yao, ``Multiobjective Neural Network
Ensembles based on Regularized Negative
Correlation Learning,'' IEEE Transactions on
Knowledge and Data Engineering, 22(12):1738-1751,
December 2010.
 
A. Chandra and X. Yao, “Ensemble learning using
multi-objective evolutionary algorithms,” Journal of
Mathematical Modelling and Algorithms, 5(4):
417-445, December 2006.
Case Study VI:
Online Learning with Concept Drift
We Are Getting New Data All the Time …
  L. L. Minku, A. White and X. Yao, ``The Impact
of Diversity on On-line Ensemble Learning in
the Presence of Concept Drift,'' IEEE
Transactions on Knowledge and Data
Engineering, 22(5):730-742, May 2010.
  F. L. Minku, H. Inoue and X. Yao, ``Negative
correlation in incremental learning,'' Natural
Computing, 8(2):289-320, June 2009.
Many Other Applications
  What I have described here are a tiny set
of applications that we have done or are
doing.
  http://www.cercia.ac.uk
Only Applications?
  Basque Center for Applied
Mathematics
Some Mathematical Challenges
  Why, when and how do evolutionary
algorithms work?
  How does an evolutionary algorithm scale?
  What is the relationship between the
computation time and the problem size?
Computational Time
Complexity Analysis
  T. Chen, K. Tang, G. Chen and X. Yao, ``Analysis of
Computational Time of Simple Estimation of Distribution
Algorithms,'' IEEE Transactions on Evolutionary
Computation, 14(1):1-22, February 2010.
  T. Chen, J. He, G. Chen and X. Yao, ``Choosing Selection
Pressure for Wide-gap Problems,'' Theoretical Computer
Science, 411(6):926-934, February 2010.
  T. Chen, J. He, G. Sun, G. Chen and X. Yao, ``A New
Approach to Analyzing Average Time Complexity of
Population-based Evolutionary Algorithms on Unimodal
Problems,'' IEEE Transactions on Systems, Man, and
Cybernetics: Part B, 39(5):1092-1106, October 2009.
Complexity Analysis in One Slide
  Model an EA using a stochastic process, e.g., a
supermartingal, where each state in the space is
a population.
  Use drift analysis to bound the computation time
of finding the global optimum
J. He and X. Yao, ``Towards an analytic framework for analysing the
computation time of evolutionary algorithms,'' Artificial Intelligence,
145(1-2):59-97, April 2003.
J. He and X. Yao, ``Drift Analysis and Average Time Complexity of
Evolutionary Algorithms,'' Artificial Intelligence, 127(1):57-85, March
2001.
Drift Analysis as a General
Framework
  Define a distance function d(x) to measure the
distance between a population x and the optimal
solution.
  Estimate the one-step mean drift of population ξ
(t) towards the optimal solution:
  E [ d(ξ(t) - ξ(t+1)) ]
  Derive some properties of the sequence, e.g.,
the first hitting time, convergence, convergence
rate, etc., through the mean drift.
  For example,
  FirstHittingTime = InitialDistance/OneStepDrift
Occasional Surprises
  Large populations might not help!
  J. He and X. Yao, ``From an Individual to a Population: An
Analysis of the First Hitting Time of Population-Based
Evolutionary Algorithms,'' IEEE Transactions on Evolutionary
Computation, 6(5):495-511, October 2002.
  T. Chen, K. Tang, G. Chen and X. Yao, “A Large Population Size
Can Be Unhelpful in Evolutionary Algorithms,” Theoretical
Computer Science, accepted on 8/2/2011.
Conclusions
  Evolutionary computation has both
interesting applications and challenging
theories.
  If you have things you want to improve,
there might be opportunities for
optimisation.
  If you have lots of data and are unsure of
what to do, there might be opportunities
for ML/DM.