Dimensions of Neural-symbolic Integration - A Structured Survey

Abstract

Research on integrated neural-symbolic systems has made significant progress in the recent past. In particular the understanding of ways to deal with symbolic knowledge within connectionist systems (also called artificial neural networks) has reached a critical mass which enables the community to strive for applicable implementations and use cases. Recent work has covered a great variety of logics used in artificial intelligence and provides a multitude of techniques for dealing with them within the context of artificial neural networks. We present a comprehensive survey of the field of neural-symbolic integration, including a new classification of system according to their architectures and abilities.

arXiv comment28 pages

References in corpus (2)

• The Integration of Connectionism and First-Order Knowledge Representation and Reasoning as a Challenge for Artificial Intelligence
• Corollaries on the fixpoint completion: studying the stable semantics by means of the Clark completion

Cited by in corpus (11)

• Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
• Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning
• On the Binding Problem in Artificial Neural Networks
• Lifted Relational Neural Networks
• Explaining Trained Neural Networks with Semantic Web Technologies: First Steps
• Beyond Graph Neural Networks with Lifted Relational Neural Networks
• Neuro-Symbolic Artificial Intelligence: Current Trends
• Reconciling the Discrete-Continuous Divide: Towards a Mathematical Theory of Sparse Communication
• Controlling Recurrent Neural Networks by Diagonal Conceptors
• Robust Deep Neural Networks Inspired by Fuzzy Logic
• Knowledge as Invariance -- History and Perspectives of Knowledge-augmented Machine Learning