ReMi: A Random Recurrent Neural Network Approach to Music Production
This work addresses musicians by offering a tool to expand creativity without replacing them, though it is incremental as it builds on existing random network methods.
The paper tackled the problem of generative AI's high energy consumption and copyright issues by using randomly initialized recurrent neural networks to produce configurable arpeggios and low-frequency oscillations, requiring no data and less computational power.
Generative artificial intelligence raises concerns related to energy consumption, copyright infringement and creative atrophy. We show that randomly initialized recurrent neural networks can produce arpeggios and low-frequency oscillations that are rich and configurable. In contrast to end-to-end music generation that aims to replace musicians, our approach expands their creativity while requiring no data and much less computational power. More information can be found at: https://allendia.com/