According to the No-Free-Lunch Theorems, it is necessary for search algorithms to incorporate some knowledge of the search space in order to perform better than random search. Incorporation of a priori knowledge, such as expert knowledge, meta-heuristics and human preferences, and most importantly domain knowledge discovered during evolutionary search, into evolutionary algorithms has gained increasing interest in the recent years. However, work on knowledge extraction and incorporation in evolutionary computation has been carried out from a wide range of research backgrounds and so far, few efforts have been made to put the diversified methods under a unified framework.

This special issue attempts to put together the state-of-art and recent advances on knowledge incorporation in evolutionary computation under a systematic and unified framework. Topics include but are not limited to:

• Different knowledge representation schemes: fuzzy logic (computing with words), production systems, semantic networks, tree structures, neural networks, Bayesian networks, short-term and long-term memories, etc.
• Knowledge extraction from history data and during evolutionary computation, etc.
• Knowledge incorporation in genetic representation and population initialization, reproduction and selection, fitness evaluation, constraint handling, preference articulation, as well as knowledge acquisition through life-time learning, cultural algorithms, human-machine interactions and agent-based systems, etc.