Music and Connectionism, edited by Peter M. Todd and D. Gareth Loy

This book stands as a survey of the field of the creative application of neural networks to create music. The work expounds the early work of David Cope from 1981 and Todd’s own earlier ideas. This includes Todd’s influential work, “A Connectionist Approach to Algorithmic Composition,” (1989) in which he describes some of the earliest creative application of the ability to “generalize” from data rather than follow programmed rules. Todd explains how a: “fundamental shift allows the development of new algorithmic composition methods that rely on learning the structure of existing musical examples and generalizing from these learned structures to compose new pieces. These methods contrast greatly with the majority of older schemes that simply follow a previously assembled set of compositional rules.” The book’s research introduced parallel distributed processing (PDP) to the field of music composition, which allowed for the generation of new musical pieces based on learned structures from existing examples. As Todd explained, this approach marked a significant shift from rule-based methods to a more dynamic, self-learning system.