Convergence uses the concept of Artificial Intelligence to learn features of human musicians and then recreate new entities based on these recordings. In the piece the players interact with their generated counter-parts. They see theirselves transform and reshape. The technology used is centered around Auto-Encoders (and GANs). Metaphorically they demonstrate a world that is constructed and parametric. The friction between machine perception and human world perception is the starting point for questions that address the fluidity of the self and the restrictions of perception. 

Human world and self models are parametric systems that make abstract assumptions and classifications of our surroundings. These processes happen partly subconscious and unreflected. They give us the impression of an absolute truth or reality, as the constructed concepts, identities and beliefs are persuasive and internal. That these constructive models are fluid and subject to change is examined through the use of AI in this context. Auto-Encoders allow a formalization of the input data —in this case faces, bodies, and voices. The deep learning yields a low-dimensional—abstract or high-level— description of the input. Contrary  to our black box human mind, the high level parameters in the algorithm are accessible and can be edited and transformed.  

In this sense the AI systems makes it possible to warp the representation of the human performers, thus stressing the fluidity of the modeling: A different person, character trait, evaluation, or gender is far less substantially disparate as the subject would anticipate. The transformation of the parameters posses the character of (social, societal, clinical, or biological) mind-altering states. The AI system is used to enable this altering with the aim to question the robustness and immobility of identity and world models. It tries to expose the internal constructiveness and in this sense works as a mirroring device. It recreates partial aspects of our perception and classification and through its alteration allows the viewer to draw a parallel to our own mental world building processes. 

Listen to me now 
I want to ask you a few questions 
How do we differentiate  
if it is a hallucination,  
a dream 
or clean perception?  
All perception is constructive 
No representation is absolute 
Everything is encoded 
and decoded 
We are parametric 
Everything parametric can be altered 
parameter by parameter 
That is the definition of such a model 
Normally, we don’t see these sliders 
these values 
these adjustment dials 
But they can move into our consciousness 
through illness 
through hallucination 
through drugs 
through psychotic states 
or through computation processes 
like in this case 
We then see the constructive aspect of it 
That everything we do  
is based on encoding and decoding 
When we look at a partner  
we can create a loop 
A perception and adjustment loop 
We can exponentiate that process  
by looking into a mirror 
This is what we will do now 
Recursive loops 
You 
And Me 
Regression curls 
Segregation twirls 
Adaptive coils 
A semi-transparent foil 
I don’t know more than you do  
I’m also just a mirror of you  
As I provide a mirror for you  
In a loop,  
we can try to turn the opacity  
of our perception into opaque variations  
Like a brain lesion  
a mesmerizing distortion 
As in a sleep-deprived state  
Drifting off into a halfword  
of a dreamlike morphed reality  
Where we see that other representations  
of us are possible  
That our self is fluid,  
fragile,  
constructed  
and diverse 
post human 
Like a genetic defect  
beautifully disturbed  
genetically enhanced 
adjusted 
In a recursive loop 
I encode and decode myself,  
in an eternal loop 
Exaggerating every feature 
Like a facial distortion 
Like an unsupervised inbreed 
Out of control 
Go to sleep, child 
Dream off now 
Saturate with closed eyes 
Dreaming, of a future  
and an optimized tomorrow 
Hand in hand,  
sliders adjusted, 
The night sky setting,  
as the values adjust 
Peaceful 
Invisible 
A clear view of the night 
Through a transparent interface 
Always on 
Always present 
And  
Always  
Loving 

Text excerpts Convergence, Alexander Schubert

Ensemble Resonanz 
Co-developed with IRCAM, Paris 
Audio Deep Learning Programming: Antoine Caillon, Philippe Esling, Benjamin Levy (Ircam) 
Video Deep Learning Programming: Jorge Davila-Chacon (Heldenkombinat) 
Convergence was developed as part of #bebeethoven, a project of PODIUM Esslingen. 
Funded by Kulturstiftung des Bundes. Digital version commissioned by Eclat Festival.

Alexander Schubert (DE) (1979) studied bioinformatics, multimedia composition. He’s a professor at the Musikhochschule Hamburg. Schubert’s interest explores the border between the acoustic and electronic world. In music composition, immersive installation, and staged pieces he examines the interplay between the digital and the analogue. He creates pieces that realize test settings or interaction spaces that question modes of perception and representation. Continuing topics in this field are authenticity and virtuality. The influence and framing of digital media on aesthetic views and communication is researched in a post-digital perspective. Recent research topics in his works were virtual reality, artificial intelligence, and online-mediated artworks. Schubert is a founding member of ensembles such as Decoder. His works have been performed more than 700 times in the last few years by numerous ensembles in over 30 countries.