Towards Automation of Creativity: A Machine Intelligence Approach

TL;DR

This paper explores computational creativity in music by studying its key aspects, formulating evaluation metrics, and proposing a prototype capable of human-level creativity, validated through benchmarks and comparisons.

Contribution

It introduces a novel algorithmic perception framework for human creativity and develops a prototype demonstrating human-level musical creativity.

Findings

Prototype achieves comparable creativity benchmarks

Demonstrates emergence of computational creativity in music

Provides a new framework for evaluating creative systems

Abstract

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.