Date of Submission

Spring 2016

Academic Programs and Concentrations

Computer Science

Project Advisor 1

Keith O'Hara

Abstract/Artist's Statement

The goal of this project was to use neural networks as a tool for live music performance. Specifically, the intention was to adapt a preexisting neural network code library to work in Max, a visual programming language commonly used to create instruments and effects for electronic music and audio processing. This was done using ConvNetJS, a JavaScript library created by Andrej Karpathy.

Several neural network models were trained using a range of different training data, including music from various genres. The resulting neural network-based instruments were used to play brief pieces of music, which they used as input to create unique musical output.

Max, while useful for live performance and audio processing, proved to be somewhat impractical for this project. Implementing too complex of a network caused performance issues and even crashing. Because of this, smaller networks, which are less robust in their prediction abilities had to be used, producing very simplistic musical patterns.

Access Agreement

Open Access

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

This work is protected by a Creative Commons license. Any use not permitted under that license is prohibited.