Neurosymbolic and Explainable Artificial Intelligence

Neurosymbolic Artificial Intelligence (other common spellings: Neural-Symbolic, Neuro-Symbolic) concerns the combination of artificial neural networks (including deep learning) with symbolic methods, e.g. from logic based knowledge representation and reasoning in artificial intelligence. We list pointers to some of the work on this issue which the Data Semantics Lab is pursuing. Explainable Artificial Intelligence is concerned with understanding and explaining the decisions made by AI systems, in particular deep learning systems; since we approach this topic using symbolic knowledge (more precisely, knowledge graphs), our work on this is also related to neuro-symbolic integration.

Call for book chapter proposals for A Compendium of Neuro-Symbolic Artificial Intelligence

Overview Articles and Links

Deductive Logical Reasoning Using Deep Learning

Explainable Artificial Intelligence Using Knowledge Graphs