Neurosymbolic AI and its Taxonomy: a survey

TL;DR

This survey reviews recent developments in neurosymbolic AI, highlighting its role in advancing towards Artificial General Intelligence by integrating symbolic reasoning with neural networks.

Contribution

It provides a comprehensive taxonomy, classification, and comparison of neurosymbolic models and their applications based on recent research papers.

Findings

Neurosymbolic AI models are diverse and evolving.

Integration of symbolic reasoning enhances neural network capabilities.

Applications span multiple AI domains.

Abstract

Neurosymbolic AI deals with models that combine symbolic processing, like classic AI, and neural networks, as it's a very established area. These models are emerging as an effort toward Artificial General Intelligence (AGI) by both exploring an alternative to just increasing datasets' and models' sizes and combining Learning over the data distribution, Reasoning on prior and learned knowledge, and by symbiotically using them. This survey investigates research papers in this area during recent years and brings classification and comparison between the presented models as well as applications.