Neural-Symbolic Learning and Reasoning: A Survey and Interpretation

TLDR

Human behaviour research spans computer science, AI, cognitive science, philosophy, and psychology, with cognition as the foundation for computational logic, connectionist, and uncertainty models, and recent work producing computationally grounded reasoning, learning, and language models. The survey examines researchers’ perspectives on neural‑symbolic learning and reasoning. The article is structured into three sections covering scope and goals, system realizations and applications, and future challenges. Integrating machine learning with automated reasoning has produced cognitive computational systems that show promise across computational biology, fault diagnosis, simulator training, and software verification.

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.