Pattern-based engineering of Neurosymbolic AI Systems

Abstract

The symbiotic combination of sub-symbolic and symbolic AI techniques is a significant trend in AI, leading to the fast-paced development of various techniques that integrate these paradigms to build intelligent systems. However, the wealth of heterogeneous architectural options for combining the paradigms into Neurosymbolic AI (NeSy-AI) systems poses significant challenges. In particular, there is currently no standardized way to design, engineer, and document such systems that encompass visual and formal notations. Existing works aim to address this challenge by systematically modelling NeSy-AI systems as design patterns that include process, data, and human interactions. However, these works focus on capturing specific views of the system rather than aiming to support the broad process of AI system engineering. This paper outlines a vision of pattern-based AI Systems engineering, aiming to support the engineering process of NeSy-AI systems with tasks such as system documentation and artefact generation through interlinked visual and formal notations with Knowledge Graphs at its core.