Dimensions of Neural-symbolic Integration - A Structured Survey

TL;DR

This survey reviews recent advances in neural-symbolic integration, categorizing various architectures and techniques for incorporating symbolic knowledge into neural networks to enhance AI capabilities.

Contribution

It provides a comprehensive classification of neural-symbolic systems based on their architectures and abilities, summarizing recent progress in the field.

Findings

Diverse logics are integrated into neural networks.

A new classification scheme for neural-symbolic systems.

Progress towards practical implementations.

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.