Machine Learning Performance

Sounds, Images and biometric Data of Birds is used to recreate their sound and behavior. Due to interpolation between different kinds and glitches in the learning algorithm the sounds start very natural and get more and more sorted and structured like in modern minimal or electronic music while the image are becoming more and more abstract and generalized. Similar to my other work every performance is very different from the others before. 3 different neural networks are interacting and used for the recreation of sound using supercollider and image using open Frameworks. Everything happens in realtime.