Structuring Concept Space with the Musical Circle of Fifths by Utilizing Music Grammar Based Activations
This work addresses the challenge of meaningful concept organization in AI, potentially benefiting deep learning algorithms, but it appears incremental as it applies existing music theory principles to a new context without broad validation.
The paper tackles the problem of structuring concept representations in neural networks by proposing a novel approach that uses musical grammar to regulate activations in a spiking neural network, resulting in a concept map organized by the musical circle of fifths.
In this paper, we explore the intriguing similarities between the structure of a discrete neural network, such as a spiking network, and the composition of a piano piece. While both involve nodes or notes that are activated sequentially or in parallel, the latter benefits from the rich body of music theory to guide meaningful combinations. We propose a novel approach that leverages musical grammar to regulate activations in a spiking neural network, allowing for the representation of symbols as attractors. By applying rules for chord progressions from music theory, we demonstrate how certain activations naturally follow others, akin to the concept of attraction. Furthermore, we introduce the concept of modulating keys to navigate different basins of attraction within the network. Ultimately, we show that the map of concepts in our model is structured by the musical circle of fifths, highlighting the potential for leveraging music theory principles in deep learning algorithms.