Neurosymbolic AI: The 3rdsuperscript3𝑟𝑑3^{rd} Wave
Artur d’Avila Garcez1 and Luís C. Lamb2 1 City, University of London, UK 2 Federal University of Rio Grande do Sul, Brazil
Abstract
Current advances in Artificial Intelligence (AI) and Machine Learning (ML) have achieved unprecedented impact across research communities and industry. Nevertheless, concerns about trust, safety, interpretability and accountability of AI were raised by influential thinkers. Many have identified the need for well-founded knowledge representation and reasoning to be integrated with deep learning and for sound explainability. Neural-symbolic computing has been an active area of research for many years seeking to bring together robust learning in neural networks with reasoning and explainability via symbolic representations for network models. In this paper, we relate recent and early research results in neurosymbolic AI with the objective of identifying the key ingredients of the next wave of AI systems. We focus on research that integrates in a principled way neural network-based learning with symbolic knowledge representation and logical reasoning. The insights provided by 20 years of neural-symbolic computing are shown to shed new light onto the increasingly prominent role of trust, safety, interpretability and accountability of AI. We also identify promising directions and challen
中文速览
深度学习在图像识别、自然语言处理等领域取得了惊人成果，但它脆弱、不可解释、需要海量数据的短板也日益暴露，这促使研究者重新思考：如何让AI既能像神经网络那样从数据中学习，又能像符号系统那样进行逻辑推理和解释？这篇综述梳理了神经符号计算（neural-symbolic computing）二十年来的核心研究成果，系统介绍了从松耦合混合系统到深度整合方案的各类方法，分析了分布式表示与局部表示之争、变量绑定、常识推理等关键技术瓶颈。研究发现，将符号逻辑与神经网络原则性地结合，能够在不牺牲学习能力的前提下显著提升AI的可解释性、鲁棒性和推理能力。这项工作的价值在于，它为构建"可信赖AI"提供了理论基础和技术路线图，并为未来十年神经符号AI的研究指明了方向，对于希望AI真正走向安全、可问责的学界和产业界而言具有重要参考意义。
原文 arXiv:2012.05876;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2012.05876v2