Symbolic AI versus Connectionism in Music Research

Abstract

In cognitive science and research on artificial intelligence, there are two central paradigms: the symbolic and the analogical. Within the analogical paradigm, interest in artificial neural networks, or connectionism, has experienced a resurgence during the last decade; this change has also been reflected in the field of musical modeling. This article provides a general survey of the relationship between symbolic AI and connectionism, both on a general level and from the point of view of music research. This is followed by a short introduction to artificial neural networks, which includes a description the main principles of their structure and function as well as a presentation examples of their use in the field of music.