Evolutionary methods for musical composition

We discuss the use of genetic algorithms (GAs) for the generation of music. We explain the structure of a typical GA, and outline existing work on the use of GAs in computer music. We propose that the addition of domain-specific knowledge can enhance the quality and speed of production of GA results, and describe two systems which exemplify this. However, we conclude that GAs are not ideal for the simulation of human musical thought (notwithstanding their ability to produce good results) because their operation in no way simulates human behaviour.