Composing Using Heterogeneous Cellular Automata

摘要

Music composition is a highly intelligent activity. Composers exploit a large number of possible patterns and creatively compose a new piece of music by weaving various patterns together in a musically intelligent manner. Many researchers have investigated algorithmic compositions and realised the limitations of knowledge elicitation and knowledge exploitation in a given representation/computation paradigm. This paper discusses the applications of heterogeneous cellular automata (hetCA) in generating chorale melodies and Bach chorales harmonisation. We explore the machine learning approach in learning rewrite-rules of cellular automata. Rewrite-rules are learned from music examples using a time-delay neural network. After the hetCA has successfully learned musical patterns from examples, new compositions are generated from the hetCA model.