Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Artificial Intelligence has developed through two main approaches: symbolic AI, which focuses on logical reasoning, and neural AI, which focuses on learning from data. While both approaches are powerful, each has its own limitations. This study proposes a unified theoretical framework that combines symbolic reasoning with neural learning, known as neuro-symbolic reasoning.
The research introduces a mathematical model that embeds logical expressions into continuous vector spaces and enables reasoning through differentiable operations. The framework ensures approximate soundness and completeness while maintaining computational feasibility. It also improves interpretability by incorporating logical constraints into neural systems.
Overall, this work provides a theoretical foundation for integrating learning and reasoning in AI and supports the development of more reliable and explainable intelligent systems.
"A Unified Theoretical Framework for Neuro-Symbolic Reasoning", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2456-3315, Vol.11, Issue 4, page no.c394-c429, April-2026, Available :http://www.ijrti.org/papers/IJRTI2604324.pdf
Downloads:
000205505
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator