DANIEL MAJONICA

Interactive AI experience for the art exhibition Talking with Color

 

• worked on as an AI Researcher and Engineer at Cross Compass

• 2 months of development time.

• a small team of highly skilled professionals.

• Description:

  • Artificial Intelligences are quickly closing the gap to human-level performance in a whole flock of tasks. Abilities that were so far considered unique to humans are now handled with ease thanks to the advent of Deep Learning techniques. These bio-inspired models aim to reproduce the variety of cognitive functions supported by the brain – vision, attention, decision, control, etc. –, and as such, they are about as hard to understand and interpret as biological neural networks are. Yet it doesn’t have to be the case, because the mechanics of these models are perfectly known. The exhibit lets the viewer immerse himself into such mechanics in a dynamic and interactive way. While the AI’s task is to apply multi-style transfer to the video feed in real-time as a demonstration of creativeness, bursts of color and of colorful patterns in the visualization of the AI’s hierarchy of internal states let the viewer’s imagination wander. Each screen acts as a different type of looking-glass. The left screen directly reflects what we see (the video feed) and perceive (convolutional layers) of the real world. In the center is shown what is called the “Latent Space”, which is an integration layer for all signals that contribute to achieving the goal of the task – here of merging different styles of transfer. In our brain, this space consists of the “Connectome”, that is, the neural wiring between various areas of our cortex. On the right, reconstruction layers (deconvolution) operate the multi-style transfer and the merge of what becomes an imaginary, distorted mirror – one might call it hallucination – of the reality.