Musical Deep Learning: Stylistic Melodic Generation with Complexity Based Similarity

Abstract

The wide-ranging impact of deep learning models implies significant application in music analysis, retrieval, and generation. Initial findings from musical application of a conditional restricted Boltzmann machine (CRBM) show promise towards informing creative computation. Taking advantage of the CRBM’s ability to model temporal dependencies full reconstructions of pieces are achievable given a few starting seed notes. The generation of new material using figuration from the training corpus requires restrictions on the size and memory space of the CRBM, forcing associative rather than perfect recall. Musical analysis and information complexity measures show the musical encoding to be the primary determinant of the nature of the generated results.