Never Ending Reasoning and Learning: Opportunities and Challenges

Sriraam Natarajan, Kristian Kersting
Proceedings of The First AAAI Bridge Program on Continual Causality, PMLR 208:71-74, 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v208-natarajan23a, title = {Never Ending Reasoning and Learning: Opportunities and Challenges}, author = {Natarajan, Sriraam and Kersting, Kristian}, booktitle = {Proceedings of The First AAAI Bridge Program on Continual Causality}, pages = {71--74}, year = {2023}, editor = {Mundt, Martin and Cooper, Keiland W. and Dhami, Devendra Singh and Ribeiro, Adéle and Smith, James Seale and Bellot, Alexis and Hayes, Tyler}, volume = {208}, series = {Proceedings of Machine Learning Research}, month = {07--08 Feb}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v208/natarajan23a/natarajan23a.pdf}, url = {https://proceedings.mlr.press/v208/natarajan23a.html}, 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.} }
Endnote
%0 Conference Paper %T Never Ending Reasoning and Learning: Opportunities and Challenges %A Sriraam Natarajan %A Kristian Kersting %B Proceedings of The First AAAI Bridge Program on Continual Causality %C Proceedings of Machine Learning Research %D 2023 %E Martin Mundt %E Keiland W. Cooper %E Devendra Singh Dhami %E Adéle Ribeiro %E James Seale Smith %E Alexis Bellot %E Tyler Hayes %F pmlr-v208-natarajan23a %I PMLR %P 71--74 %U https://proceedings.mlr.press/v208/natarajan23a.html %V 208 %X 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.
APA
Natarajan, S. & Kersting, K.. (2023). Never Ending Reasoning and Learning: Opportunities and Challenges. Proceedings of The First AAAI Bridge Program on Continual Causality, in Proceedings of Machine Learning Research 208:71-74 Available from https://proceedings.mlr.press/v208/natarajan23a.html.

Related Material