JOURNAL ARTICLE

Towards Neurosymbolic AI: Hybrid Models for Coupling Deductive and Inductive Reasoning, Special Issue Featuring Extended Papers from HYDRA 2024.

  • Published In: Intelligenza Artificiale, 2025, v. 19, n. 2. P. 83 1 of 3

  • Database: Academic Search Ultimate 2 of 3

  • Authored By: Bruno, Pierangela; Calimeri, Francesco; Cauteruccio, Francesco; Terracina, Giorgio 3 of 3

Abstract

The article focuses on the integration of deductive and inductive reasoning in Artificial Intelligence (AI) through the emerging field of Neurosymbolic AI. It discusses the limitations of traditional symbolic and sub-symbolic approaches and highlights the potential of hybrid models to enhance AI's reasoning capabilities. The article presents three contributions from the HYDRA 2024 Workshop, showcasing innovative methodologies that combine logic-based and data-driven techniques. These contributions include a neurosymbolic approach for tackling the ARC-AGI challenge, an evaluation of Large Language Models (LLMs) in program synthesis, and a framework for improving curriculum coherence in higher education through a hybrid design. Each work emphasizes the importance of merging symbolic and subsymbolic methods to achieve more robust and explainable AI systems. [Extracted from the article]

Additional Information

  • Source:Intelligenza Artificiale. 2025/08, Vol. 19, Issue 2, p83
  • Document Type:Editorial
  • Subject Area:Health and Medicine
  • Publication Date:2025
  • ISSN:1724-8035
  • DOI:10.1177/17248035251364905
  • Accession Number:187409752
  • Copyright Statement:Copyright of Intelligenza Artificiale is the property of Sage Publications Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Looking to go deeper into this topic? Look for more articles on EBSCOhost.