Towards Automation of Creativity: A Machine Intelligence Approach
It addresses the challenge of computational creativity for music generation, but appears incremental as it builds on existing notions and systems.
This paper tackles the problem of automating creativity in music by studying and formulating different aspects of creativity, proposing a prototype that demonstrates human-level creativity, and validating it against benchmarks and existing systems.
This paper demonstrates emergence of computational creativity in the field of music. Different aspects of creativity such as producer, process, product and press are studied and formulated. Different notions of computational creativity such as novelty, quality and typicality of compositions as products are studied and evaluated. We formulate an algorithmic perception on human creativity and propose a prototype that is capable of demonstrating human-level creativity. We then validate the proposed prototype by applying various creativity benchmarks with the results obtained and compare the proposed prototype with the other existing computational creative systems.