Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniques
This work addresses the problem of enhancing AI reasoning and learning capabilities for researchers and practitioners in neuro-symbolic AI, but it appears incremental as it builds on existing symbolic knowledge injection techniques.
The paper tackles the limitations of deep learning models, such as data dependency and lack of transparency, by proposing solutions to improve symbolic knowledge injection and integrate machine learning with logic in multi-agent systems.
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).