A friend, Carola, sent me the open call as she knew I was working on an AI-driven research & project. To be honest we were really lucky with timings, since I was finishing Adversarial Feelings when I decided to participate…

I am interested in employing neural networks as performative tools. I am fascinated by the idea to drive machines to perform human emotions… it is an occasion to observe human behaviors from the outside, or at least to observe what machines perceive as significant about our feelings. Which is sometimes really surprising and uncanny. Especially when working with text and music, Neural Networks offer the possibility to deal with the unconscious in many ways.

I think artificial intelligence is an effective tool to melt languages, and to translate data into different combined media. At the moment I’m trying to start from text, to create AI generated narrative artworks, where audiovisual events follow a generated “neural” plot.

That of latent space is a really representative concept in the world we live in. A latent space is a multidimensional space (a matrix) where all the possible features of a NN lies. It means that (for instance in the famous CelebGAN I used for the video of ‘3402 Selves’) it’s the space where all the faces the NN could generate lies. Well, this multidimensional space, just like the truth in post-digital age, is LATENT: it Can’t be observed directly, but we can “explore” it through interpolations and other operational functions. And LSs don’t deal with time directly. Every single timebased narration we produce by exploring a certain path within the latent space is a representation of the latent space itself, but it never resolves in any way the whole content, which is by definition non representable.

LOREM - "Adversarial Feelings" - ReHumanism Art Prize


Lorem is a music-driven multidisciplinary project by Italian sound and visual artist Francesco D’Abbraccio. It is an inquiry about Human-Computer Interaction in the age of Artificial Intelligence. During the last two years Lorem built a collaborative platform, involving AI artists (Mario Klingemann, Damien Henry), video artists (Karol Sudolski, Mirek Hardiker), information engineering researchers (Nicola Cattabiani) with the aim to produce original audio, visuals and lyrics. Deep neural networks, hacked hardware and programmed errors are used to drive machines toward aesthetical, autonomous behaviours.

Website: studio–frames.com

"Adversarial Feelings"

Description of the work

The idea that data are THE new form of Value is broadly agreed nowadays, and it speaks a lot about the emergency of Neural Networks in economic driven contexts. AI is actually one of the most affective tools to interpretate and manipulate huge amounts of information, and to implement predictive models. On the other hand, Neural Networks are the more and more employed to simulate human behaviours, in order to address user activities. Once trained on human gestures, AI systems develop a mimetic attitude, becoming the more and more capable to blend into human irrational and instinctual processes. “Adversarial Feelings” is an investigation focusing on politics of representation of such powerful, sometimes dangerous devices. Rather then employ machines to affect users, the project is an attempt to teach computers to express human (and non-human) complex feelings. Based on self-generating MIDI polyrhythms and on recursive audio resampling, “Adversarial Feelings” is AV installation where intricated music patterns discloses emotional time-fractured experiences. To develop his “intelligent system”, Lorem involved AI artists (Mario Klingemann, Damien Henry), video artists (Karol Sudolski, Mirek Hardiker) and engineering of information researchers (Nicola Cattabiani) with the aim to produce original music, visuals and lyrics

Want to know the other finalists?