Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning

Abstract

Current advances in Artificial Intelligence and machine learning in general, and deep learning in particular have reached unprecedented impact not only across research communities, but also over popular media channels. However, concerns about interpretability and accountability of AI have been raised by influential thinkers. In spite of the recent impact of AI, several works have identified the need for principled knowledge representation and reasoning mechanisms integrated with deep learning-based systems to provide sound and explainable models for such systems. Neural-symbolic computing aims at integrating, as foreseen by Valiant, two most fundamental cognitive abilities: the ability to learn from the environment, and the ability to reason from what has been learned. Neural-symbolic computing has been an active topic of research for many years, reconciling the advantages of robust learning in neural networks and reasoning and interpretability of symbolic representation. In this paper, we survey recent accomplishments of neural-symbolic computing as a principled methodology for integrated machine learning and reasoning. We illustrate the effectiveness of the approach by outlining the main characteristics of the methodology: principled integration of neural learning with symbolic knowledge representation and reasoning allowing for the construction of explainable AI systems. The insights provided by neural-symbolic computing shed new light on the increasingly prominent need for interpretable and accountable AI systems.

References in corpus (5)

• The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
• Neuro-Symbolic Program Synthesis
• Dimensions of Neural-symbolic Integration - A Structured Survey
• TensorLog: Deep Learning Meets Probabilistic DBs
• Propositional Knowledge Representation and Reasoning in Restricted Boltzmann Machines

Cited by in corpus (26)

• Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
• Logic Tensor Networks
• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges
• DEPTWEET: A Typology for Social Media Texts to Detect Depression Severities
• Injecting Knowledge in Data-driven Vehicle Trajectory Predictors
• Towards Explainable Neural-Symbolic Visual Reasoning
• Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment
• Beyond Graph Neural Networks with Lifted Relational Neural Networks
• Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers
• ProTo: Program-Guided Transformer for Program-Guided Tasks
• A Survey of Knowledge-based Sequential Decision Making under Uncertainty
• Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases
• A conditional, a fuzzy and a probabilistic interpretation of self-organising maps
• Explainable Goal-Driven Agents and Robots -- A Comprehensive Review
• From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
• Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
• Self-organized inductive reasoning with NeMuS
• Design considerations for a hierarchical semantic compositional framework for medical natural language understanding
• From Common Sense Reasoning to Neural Network Models through Multiple Preferences: an overview
• EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case
• A Logical Neural Network Structure With More Direct Mapping From Logical Relations
• Neural Networks Enhancement with Logical Knowledge
• Understanding in Artificial Intelligence
• Toward Building Science Discovery Machines
• Using Meta-Knowledge Mined from Identifiers to Improve Intent Recognition in Neuro-Symbolic Algorithms
• Neuro-Symbolic Forward Reasoning