Neuro-symbolic Artificial Intelligence The State Of The Art Pdf ((top))

Neuro-symbolic AI aims to integrate the connectionist (neural networks) and symbolic (rule-based) approaches to AI. This integration enables models to leverage the strengths of both paradigms: the ability to learn from data and the ability to reason and explain.

Used heavily in video understanding and robotics. The system parses a video into a symbolic scene graph (neural perception) and then learns physics rules or causal relationships using symbolic solvers (symbolic reasoning).

The current state of the art (SOTA) is frequently documented in the foundational book .