Weidi Zhang, Jieliang Luo
2nd floor, room 2611
This VR project is a conceptual response to the concept of ground truth in the AI age. From a neural network (NN) trained to recognize thousands of objects, to a NN that can only generate binary outputs, each NN, like a human being, has its own understanding of the real world. Lavin provides an immersive, responsive experience to visually explore one understanding of a NN in which the 11 real world is mapped to less than a hundred daily objects. Lavin constantly analyzes the real world via a camera and outputs semantic interpretations.