[论文解读] Neural-Symbolic Learning and Reasoning: A Survey and Interpretation

Tarek R. Besold, Artur d’Avila Garcez+12 more|arXiv (Cornell University)|Nov 10, 2017

Neural Networks and Applications参考文献 17被引用 238

一句话总结

本综述综合神经-符号学习与推理，评述原理、机制、体系结构（如 NSCA）及其应用，并讨论挑战与未来方向。

ABSTRACT

The study and understanding of human behaviour is relevant to computer science, artificial intelligence, neural computation, cognitive science, philosophy, psychology, and several other areas. Presupposing cognition as basis of behaviour, among the most prominent tools in the modelling of behaviour are computational-logic systems, connectionist models of cognition, and models of uncertainty. Recent studies in cognitive science, artificial intelligence, and psychology have produced a number of cognitive models of reasoning, learning, and language that are underpinned by computation. In addition, efforts in computer science research have led to the development of cognitive computational systems integrating machine learning and automated reasoning. Such systems have shown promise in a range of applications, including computational biology, fault diagnosis, training and assessment in simulators, and software verification. This joint survey reviews the personal ideas and views of several researchers on neural-symbolic learning and reasoning. The article is organised in three parts: Firstly, we frame the scope and goals of neural-symbolic computation and have a look at the theoretical foundations. We then proceed to describe the realisations of neural-symbolic computation, systems, and applications. Finally we present the challenges facing the area and avenues for further research.

研究动机与目标

• 界定神经符号计算的范围与目标，并回顾理论基础。
• 描述神经符号计算的实现、系统与应用。
• 讨论该领域面临的挑战并勾画未来研究方向。

提出的方法

• 提出一个在多个抽象层次上结合逻辑与连接主义模型的统一视角。
• 解释 fibring 作为将网络耦合并整合符号与子符号推理的机制。
• 描述符号理论与神经表示之间的翻译算法及其回传。
• 以 NSCA 系统为具体应用示例，演示学习与推理。
• 强调模块化、分层的网络架构如何支持具表达能力的神经符号系统。

实验结果

研究问题

• RQ1 哪些原理、机制与体系结构构成神经-符号学习与推理的基础？
• RQ2 神经网络如何实现、论证并提取符号知识以实现稳健推理？
• RQ3 实际应用有哪些？神经-符号系统在真实世界任务中的表现如何？
• RQ4 在跨越抽象层次整合学习与推理方面还有哪些挑战？

主要发现

• 神经-符号系统通过在逻辑与网络之间进行翻译，将鲁棒学习与符号推理结合。
• 模块化和分层结构是常见的设计特征，可提升表达能力和可维护性。
• Fibring 通过连接表示不同知识层次的网络，实现多层级集成。
• NSCA 展示从不确定观测中学习时间关系并提取时间逻辑规则。
• RTRBMs及相关架构在认知代理框架中实现对连续数据的概率性、时序推理。
• 应用涵盖生物信息学、故障诊断、训练仿真器和多模态处理。