Abstract

In this paper we explore synergies between the machine learning and knowledge representation fields by considering how scientific knowledge is represented in these areas. We illustrate some of the knowledge obtained through machine learning methods, providing two contrasting examples of such models: probabilistic graphical models (aka Bayesian networks) and artificial neural networks (including deep learning networks). From knowledge representation, we give an overview of ontological representations, qualitative reasoning, and planning. Then we discuss potential synergies that would benefit both areas.

Date

March 14, 2026

Authors

Imme Ebert-Uphoff, Yolanda Gil

Journal

Proceedings of the 1st International Workshop on Capturing Scientific Knowledge. Palisades, NY