Correia, Marisol B.Fonseca, C. M.2012-02-162012-02-1620072007 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-10, PROCEEDINGS Book Series: IEEE Congress on Evolutionary Computation Pages: 2842-2849 DOI: 10.1109/CEC.2007.4424832 Published: 2007978-1-4244-1339-3AUT: MCO00732;http://hdl.handle.net/10400.1/902An experimental study was performed to determine whether it is neutrality itself or the larger neighborhoods associated with neutral representations that allow good results to be achieved on NK fitness landscape problems. Markov chains were used to model a stochastic hill climber on NK fitness landscapes, using three types of representation: a neutral network representation, a redundant representation without neutrality which exhibits the same neighborhood of the neutral representation and a non-redundant representation.engEvolutionary ComputationRedundant representationsNeutralityError control codesNK fitness landscapesconference object