Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
https://arxiv.org/abs/1711.03902
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 behavi
our, among the most prominent tools in the modelling of behaviour are computat
ional-logic systems, connectionist models of cognition, and models of uncertai
nty. Recent studies in cognitive science, artificial intelligence, and psychol
ogy have produced a number of cognitive models of reasoning, learning, and lan
guage that are underpinned by computation. In addition, efforts in computer sc
ience 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 dia
gnosis, training and assessment in simulators, and software verification. This
joint survey reviews the personal ideas and views of several researchers on n
eural-symbolic learning and reasoning. The article is organised in three parts
: Firstly, we frame the scope and goals of neural-symbolic computation and hav
e a look at the theoretical foundations. We then proceed to describe the reali
sations of neural-symbolic computation, systems, and applications. Finally we
present the challenges facing the area and avenues for further research.