Symbolic AI
Symbolic AI, aiming to imbue artificial intelligence with human-like reasoning and explainability, seeks to integrate the strengths of symbolic logic and reasoning with the learning capabilities of connectionist (neural network) approaches. Current research focuses on hybrid neuro-symbolic architectures, such as Logic Tensor Networks and neuro-vector-symbolic systems, to improve model interpretability, generalization, and robustness while leveraging the power of large language models. This interdisciplinary field holds significant promise for advancing AI safety, trustworthiness, and the development of more reliable and explainable AI systems across diverse applications, including cybersecurity and healthcare.
Papers
Building Trustworthy AI: Transparent AI Systems via Large Language Models, Ontologies, and Logical Reasoning (TranspNet)
Fadi Al Machot, Martin Thomas Horsch, Habib Ullah
Symbolic-AI-Fusion Deep Learning (SAIF-DL): Encoding Knowledge into Training with Answer Set Programming Loss Penalties by a Novel Loss Function Approach
Fadi Al Machot, Martin Thomas Horsch, Habib Ullah