Neural-Symbolic Learning and Reasoning: A Survey and Interpretation

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.

58 pages, work in progress

Cited by in corpus (22)

• Deep Learning: A Critical Appraisal
• Exploring the landscapes of "computing": digital, neuromorphic, unconventional -- and beyond
• Neurosymbolic Reinforcement Learning and Planning: A Survey
• Discrete and continuous representations and processing in deep learning: Looking forward
• Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge
• A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence
• Faster-LTN: a neuro-symbolic, end-to-end object detection architecture
• ProTo: Program-Guided Transformer for Program-Guided Tasks
• Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning
• From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
• Collaboratively boosting data-driven deep learning and knowledge-guided ontological reasoning for semantic segmentation of remote sensing imagery
• Embedding Symbolic Knowledge into Deep Networks
• NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
• Neurosymbolic AI for Situated Language Understanding
• On the Capabilities of Pointer Networks for Deep Deductive Reasoning
• Neuro-Symbolic VQA: A review from the perspective of AGI desiderata
• Completion Reasoning Emulation for the Description Logic EL+
• Automated Fact-Checking: A Survey
• Knowledge as Invariance -- History and Perspectives of Knowledge-augmented Machine Learning
• Using Meta-Knowledge Mined from Identifiers to Improve Intent Recognition in Neuro-Symbolic Algorithms
• Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modelling
• Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning