Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniques

TL;DR

This paper explores integrating neural networks with symbolic reasoning using neuro-symbolic AI to enhance learning, reasoning, transparency, and robustness in AI systems.

Contribution

It proposes improved symbolic knowledge injection techniques and integration of ML and logic into multi-agent systems, advancing neuro-symbolic AI capabilities.

Findings

Enhanced knowledge injection methods for neuro-symbolic systems

Successful integration of ML and logic in multi-agent frameworks

Improved transparency and robustness in AI models

Abstract

Deep Learning (DL) models have become popular for solving complex problems, but they have limitations such as the need for high-quality training data, lack of transparency, and robustness issues. Neuro-Symbolic AI has emerged as a promising approach combining the strengths of neural networks and symbolic reasoning. Symbolic knowledge injection (SKI) techniques are a popular method to incorporate symbolic knowledge into sub-symbolic systems. This work proposes solutions to improve the knowledge injection process and integrate elements of ML and logic into multi-agent systems (MAS).