On the roles of redundancy and neutrality in evolutionary optimization

An experimental study was performed to explore whether it is neutrality itself or simply the larger neighborhoods associ- ated with neutral representations that influence the results achieved by evolutionary algorithms on NK fitness landscape problems. Markov chains were used to model the behaviour of a stochastic hill-climber on NK fitness landscapes, using two different types of representation: a neutral network rep- resentation which exhibits neutrality and a redundant rep- resentation without neutrality which implements the same neighborhood induced by the corresponding neutral repre- sentation