Grounded compositionality in AI,
Professor Aldo Gangemi
Grounded compositionality in AI
UKRI Centre for Doctoral Training in Safe and Trusted AI
31 Mar 2021 15:00 - 16:00 (CEST) click to join the meeting https://bit.ly/3frvcqg
Abstract:
We are facing a quantum leap in scalable approaches to Machine Intelligence (MI), but there seems to be a gap between (a) the impressive ability of MI to mimic predictive interaction and contextual adaptiveness, and (b) its substantial ignorance about the reasons why that ability concerns anything humans are interested in. The gap can be described as a lack of grounding in the compositional features of AI, be them symbolic or sub-symbolic, uni- or multi-modal, informed by background knowledge and representational learning, or not.
I will present some challenges and partial solutions to grounded compositionality in AI, and will discuss a few positions on the matter of AI evaluation, based on mixed technical and foundational issues.