Bridging the Gap Between AI and Reality • Rhodes, Greece
Time: Monday, 3.11
Room: Room A
Authors: Alvaro Velasquez
Abstract: The Chat-GPT moment demonstrated that ubiquitously useful generalization is possible for AI foundation models. However, this capability is limited by classical assumptions on machine learning models, such as the test distribution matching the training distribution, and the manifold hypothesis of relying on shared simple features across an otherwise complex dataset. These assumptions raise a critical question: how can AI generalize outside of such domains? In this talk, we mention how the foregoing assumptions are violated for important problems in autonomy, synthetic biology, logistics, and creative scientific discovery. We posit that, at some level of abstraction, the shared symbolic structures across domains will enable greater generalization and present research directions for neurosymbolic AI to achieve this vision of symbolic generalization that is robust to the gaps between AI and reality.