Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175483,
        author = {Parth Pawar and Manish},
        title = {Perception to Logic: The Rise of Neuro-Symbolic Artificial Intelligence},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {2815-2824},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175483},
        abstract = {Neuro-Symbolic AI is an emerging field that combines the strengths of neural networks and symbolic reasoning to create more intelligent and interpretable AI systems. While deep learning excels at pattern recognition and data-driven tasks, it struggles with reasoning, generalization, and explainability. Symbolic AI, on the other hand, offers logical inference and structured knowledge but lacks adaptability. By integrating both, Neuro-Symbolic AI aims to bridge these gaps. This hybrid approach enhances performance across domains like NLP, computer vision, robotics, and decision-making by enabling systems to both learn and reason. Recent advances include differentiable programming, knowledge graphs, and hybrid architectures that combine statistical learning with rule-based logic. The field is moving toward creating AI that can explain decisions, adapt to new contexts, and reason like humans—offering more scalable, transparent, and trustworthy solutions for real-world challenges.},
        keywords = {Neuro-Symbolic AI, Deep Learning, Symbolic Reasoning, Knowledge Representation Artificial Intelligence, Hybrid Systems, Machine Learning, Interpretability, Generalization, Natural Language Understanding, Computer Vision, Logical Reasoning.},
        month = {April},
        }