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

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).

In Proceedings ICLP 2023, arXiv:2308.14898

References in corpus (3)

• A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks
• Incorporating Domain Knowledge into Deep Neural Networks
• RCA: Region Conditioned Adaptation for Visual Abductive Reasoning