Editing Genetic algorithm (section)

== The building block hypothesis ==
Genetic algorithms are simple to implement, but their behavior is difficult to understand. In particular, it is difficult to understand why these algorithms frequently succeed at generating solutions of high fitness when applied to practical problems. The building block hypothesis (BBH) consists of:

# A description of a heuristic that performs adaptation by identifying and recombining "building blocks", i.e. low order, low defining-length [[Schema (genetic algorithms)|schemata]] with above average fitness.
# A hypothesis that a genetic algorithm performs adaptation by implicitly and efficiently implementing this heuristic.

Goldberg describes the heuristic as follows:

:"Short, low order, and highly fit schemata are sampled, [[crossover (genetic algorithm)|recombined]] [crossed over], and resampled to form strings of potentially higher fitness. In a way, by working with these particular schemata [the building blocks], we have reduced the complexity of our problem; instead of building high-performance strings by trying every conceivable combination, we construct better and better strings from the best partial solutions of past samplings.

:"Because highly fit schemata of low defining length and low order play such an important role in the action of genetic algorithms, we have already given them a special name: building blocks. Just as a child creates magnificent fortresses through the arrangement of simple blocks of wood, so does a genetic algorithm seek near optimal performance through the juxtaposition of short, low-order, high-performance schemata, or building blocks."{{sfn|Goldberg|1989|p=41}}

Despite the lack of consensus regarding the validity of the building-block hypothesis, it has been consistently evaluated and used as reference throughout the years. Many [[estimation of distribution algorithm]]s, for example, have been proposed in an attempt to provide an environment in which the hypothesis would hold.<ref>{{cite book|last1=Harik|first1=Georges R.|last2=Lobo|first2=Fernando G.|last3=Sastry|first3=Kumara|title=Scalable Optimization via Probabilistic Modeling |chapter=Linkage Learning via Probabilistic Modeling in the Extended Compact Genetic Algorithm (ECGA) |volume=33|date=1 January 2006|pages=39–61|doi=10.1007/978-3-540-34954-9_3|language=en|series=Studies in Computational Intelligence|isbn=978-3-540-34953-2}}</ref><ref>{{cite book|last1=Pelikan|first1=Martin|last2=Goldberg|first2=David E.|last3=Cantú-Paz|first3=Erick|title=BOA: The Bayesian Optimization Algorithm|journal=Proceedings of the 1st Annual Conference on Genetic and Evolutionary Computation - Volume 1|date=1 January 1999|pages=525–532|url=http://dl.acm.org/citation.cfm?id=2933973|isbn=9781558606111|series=Gecco'99}}</ref> Although good results have been reported for some [[List of complexity classes|classes of problem]]s, skepticism concerning the generality and/or practicality of the building-block hypothesis as an explanation for GAs' efficiency still remains. Indeed, there is a reasonable amount of work that attempts to understand its limitations from the perspective of estimation of distribution algorithms.<ref>{{cite book|last1=Coffin|first1=David|last2=Smith|first2=Robert E.|title=Linkage in Evolutionary Computation |chapter=Linkage Learning in Estimation of Distribution Algorithms |volume=157|date=1 January 2008|pages=141–156|doi=10.1007/978-3-540-85068-7_7|language=en|series=Studies in Computational Intelligence|isbn=978-3-540-85067-0}}</ref><ref>{{cite journal|last1=Echegoyen|first1=Carlos|last2=Mendiburu|first2=Alexander|last3=Santana|first3=Roberto|last4=Lozano|first4=Jose A.|title=On the Taxonomy of Optimization Problems Under Estimation of Distribution Algorithms|journal=Evolutionary Computation|date=8 November 2012|volume=21|issue=3|pages=471–495|doi=10.1162/EVCO_a_00095|pmid=23136917|s2cid=26585053|issn=1063-6560}}</ref><ref>{{cite book|last1=Sadowski|first1=Krzysztof L.|last2=Bosman|first2=Peter A.N.|last3=Thierens|first3=Dirk|title=Proceedings of the 15th annual conference on Genetic and evolutionary computation |chapter=On the usefulness of linkage processing for solving MAX-SAT |date=1 January 2013|pages=853–860|doi=10.1145/2463372.2463474|isbn=9781450319638|series=Gecco '13|hdl=1874/290291|s2cid=9986768}}</ref>