Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AI
Zishen Wan, Che-Kai Liu, Hanchen Yang, Chaojian Li, Haoran You, Yonggan Fu, Cheng Wan, Tushar Krishna, Yingyan Lin, Arijit Raychowdhury
TL;DR
NSAI addresses the demand for more efficient, robust, and explainable AI by integrating neural, symbolic, and probabilistic reasoning. The paper surveys recent NSAI algorithms, profiles three representative models to reveal runtime bottlenecks and workload characteristics, and discusses system- and architecture-level challenges and opportunities. It identifies needs in dataset development, unified neuro-symbolic-probabilistic modeling, modular software frameworks, benchmarking, and cognitive hardware design, advocating cross-disciplinary co-design and hardware-software co-optimization. The work aims to guide researchers and practitioners toward scalable, interpretable, and trustworthy NSAI systems with potential impact on human-AI collaboration and cognitive computing.
Abstract
The remarkable advancements in artificial intelligence (AI), primarily driven by deep neural networks, have significantly impacted various aspects of our lives. However, the current challenges surrounding unsustainable computational trajectories, limited robustness, and a lack of explainability call for the development of next-generation AI systems. Neuro-symbolic AI (NSAI) emerges as a promising paradigm, fusing neural, symbolic, and probabilistic approaches to enhance interpretability, robustness, and trustworthiness while facilitating learning from much less data. Recent NSAI systems have demonstrated great potential in collaborative human-AI scenarios with reasoning and cognitive capabilities. In this paper, we provide a systematic review of recent progress in NSAI and analyze the performance characteristics and computational operators of NSAI models. Furthermore, we discuss the challenges and potential future directions of NSAI from both system and architectural perspectives.