AI is now used in many areas of our daily life, however we still have difficulties to make machines interact with our world as we perceive it. Humans mainly use two types of reasoning to grasp reality: inductive and deductive reasoning. In AI, inductive reasoning is possible thanks to the use of machine learning models, while deductive reasoning can be provided by the use of ontologies. Based on these statements, we have conducted a review of articles combining the use of machine learning and ontologies in order to identify the most recent techniques that combine induction and deduction within an AI. This systematic literature review allowed us, after reading 128 studies, to identify three main groups of hybridization between machine learning and ontologies: learning-enhanced ontologies, semantic data mining and learning and reasoning system. The combination of these two types of reasoning allows machines to be better informed about the specificity of our world.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.