Reproduce “Neuro-Symbolic Artificial Intelligence: Current Trends” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Md Kamruzzaman Sarker, Lu Zhou, Aaron Eberhart, Pascal Hitzler
A review of Neuro-Symbolic Artificial Intelligence (NeSy AI) identifies a significant increase in mainstream research activity and explores the evolving architectural patterns and logical integration approaches. The analysis confirms increased adoption of first-order logic in recent systems but highlights gaps in addressing crucial aspects like error recovery and out-of-distribution generalization.
Key insights
- Neuro-Symbolic AI has experienced a substantial resurgence and mainstream adoption, with a dramatic increase in publications at leading AI conferences since 2016.
- Current NeSy AI systems predominantly employ integrated, connectionist deep learning architectures with distributed representations, a shift from earlier approaches.
- There is a notable advancement in handling more expressive logics, with a significant increase in research incorporating first-order logic, overcoming prior limitations.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.