Self-organized logic inference through 2-satisfiability dynamics in neural energy systems

Yueling Guo, Nur Ezlin Zamri, Alyaa Alway, Suad Abdeen, Mohd Shareduwan Mohd Kasihmuddin, Jia Li, Mohd. Asyraf Mansor, Yunjie Chang and Qianhong Zhang

Chaos, Solitons & Fractals, 2026, vol. 209, issue P1

Abstract: The integration of symbolic reasoning and neural dynamics provides a promising nonlinear-systems perspective for understanding how logic constraints emerge within distributed computational media. Existing neuro-symbolic architectures often suffer from instability and overfitting when reasoning over complex logical manifolds such as 3-Satisfiability, revealing unresolved issues of dynamic equilibrium and self-organization in high-dimensional information spaces. To address these challenges, this study introduces a Forward 2-Satisfiability Reverse Analysis (F2SATRA) framework based on the Discrete Hopfield Neural Network (DHNN), in which mean-field interactions and energy-minimization principles govern the fusion of multiple information sources. From the standpoint of nonlinear dynamics, the proposed system performs decision-level fusion through the co-evolution of symbolic rules and neural states, producing emergent attractors that correspond to stable logical solutions. Analytical formulations demonstrate that F2SATRA reduces redundant attributes while preserving the energetic consistency of the decision landscape. Numerical experiments further reveal the framework's capacity to maintain global stability and robustness under imbalanced conditions, indicating potential applications to complex, self-organizing decision systems. The results provide new insights into nonlinear information fusion, collective reasoning, and energy-based logic computation within the broader context of nonlinear science and complex adaptive networks.

Keywords: Symbolic reasoning; Discrete hopfield neural network; Forward selection; Nonlinear information fusion; Energy-based logic computation (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960077926005163
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:chsofr:v:209:y:2026:i:p1:s0960077926005163

DOI: 10.1016/j.chaos.2026.118375

Access Statistics for this article

Chaos, Solitons & Fractals is currently edited by Stefano Boccaletti and Stelios Bekiros

More articles in Chaos, Solitons & Fractals from Elsevier
Bibliographic data for series maintained by Thayer, Thomas R. ().