I have had an idea if I apply the neural network to create my sound work for long time. When I had a performance at Centre Pompidou with Peter Rehberg and other friends I tried to talk about the idea with a French guy from IRCAM. But, he couldn’t understand my idea, which by using neural network the sound I create would never have any repetitions.
That was 2002 and I had to wait until 2015 when I had a grant from New York State Council on the Arts through Issue Project Room, then its director Lawrence Kumpf applied for my new work. The grant finally made possible for making my cherished idea, the neural network piece, reality.
I had talked about the idea with Prof. Tony Myatt at Surrey University, UK and he developed the software for the piece with a team included Dr. Paul Modler. At the lab in the University a series of my performances of my MP3 Deviation were captured and used to train Kohonen Neural Networks to develop artificial intelligences that simulate my performances. Hence a birth of new piece AI Deviations.
I had a premiere at Issue Project Room on June 9th 2016 and the venue was more than packed and here is the performance of the piece.
(Yasunao Tone)