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

TLDR

Artificial intelligence, especially deep learning, has achieved unprecedented impact across research and media, yet concerns about its interpretability and accountability have highlighted the need for principled knowledge representation and reasoning, prompting the neural‑symbolic computing field to integrate learning and symbolic reasoning. This paper surveys recent accomplishments of neural‑symbolic computing as a principled methodology for integrating machine learning and reasoning. It outlines the methodology’s key features: principled integration of neural learning with symbolic knowledge representation and reasoning to build explainable AI systems. The insights reveal the growing necessity for interpretable and accountable AI systems.

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.