Publication
Never Ending Reasoning and Learning: Opportunities and Challenges
Sriraam Natarajan; Kristian Kersting
In: Martin Mundt; Keiland W. Cooper; Devendra Singh Dhami; Adéle Ribeiro; James Seale Smith; Alexis Bellot; Tyler L. Hayes (Hrsg.). AAAI Bridge Program on Continual Causality. AAAI Conference on Artificial Intelligence (AAAI-2023), February 7-8, Washington, DC, USA, Pages 71-74, Proceedings of Machine Learning Research, Vol. 208, PMLR, 2023.
Abstract
Inspired by the motivation behind the Never-Ending Language Learner (NELL), a continual learning system that reads the web, we propose the never-ending reasoning and learning paradigm and one instance: the Never-Ending Reasoner and Learner (NERL), which continuously learns and reasons with causal models by actively interacting with domain experts. NERL necessitates tight synergistic interaction between different communities—continual learning, causal modeling, statistical relational AI, and human-allied AI communities. We motivate NERL using the real, high-impact problem of global mitigation of adverse pregnancy outcomes, present the challenges in this system, and highlight the potential opportunities that provide for interdisciplinary collaborations.