Open Access
NEUROSYMBOLIC AI: MERGING DEEP LEARNING AND LOGICAL REASONING FOR ENHANCED EXPLAINABILITY
4
Institute for Data Science, ETH Zürich, Switzerland
4
Department of Electrical Engineering and Computer Sciences, UC Berkeley, USA
Abstract
Neurosymbolic Artificial Intelligence (AI) represents a promising paradigm that bridges the gap between sub-symbolic learning and symbolic reasoning by integrating deep learning models with formal logic-based systems. This hybrid approach leverages the pattern recognition strengths of neural networks and the interpretability and generalization power of symbolic reasoning. The convergence of these two methodologies addresses key challenges in AI, such as explainability, data efficiency, and reasoning under uncertainty. This paper explores the conceptual foundations, architectures, and recent advancements in neurosymbolic systems, highlighting their applications in domains requiring high levels of transparency and human-aligned reasoning, such as healthcare, legal systems, and scientific discovery. Furthermore, the study discusses open research questions and future directions aimed at developing scalable, robust, and interpretable AI systems.
Keywords
Neurosymbolic AI,
Deep Learning,
Symbolic Reasoning,
Explainable AI
References
Garcez, A. d’Avila; Lamb, L. C.; Gabbay, D. M. Neurosymbolic AI: The 3rd Wave (Book), 2022.
Besold, T. R.; d’Avila Garcez, A. S. et al. “Neurosymbolic AI: Bridging Learning and Reasoning,” AI Magazine, 2020.
Rocktäschel, T.; Riedel, S. “End to End Differentiable Proving,” NeurIPS, 2017.
Cai, T.; Wang, Y.; Weinberger, K. Q.; Chen, Z. “Neural Logic Machines,” NeurIPS, 2019.
Manhaeve, R.; Demeester, T.; Dumancic, S.; Davis, J.; De Raedt, L. “DeepProbLog: Neural Probabilistic Logic Programming,” NeurIPS, 2018.
Yang, F.; Yang, G.; Mooney, R. J. “Learning to Prove Theorems via Interpretable Neural Networks,” AAAI, 2020.
Wang, Y.; Wang, Z.; Manning, C. D. “Logical Neural Networks,” AAAI, 2021.
Richardson, M.; Domingos, P. “Markov Logic Networks,” Machine Learning, 2006.
Evans, R.; Saxton, D.; Amos, D.; Kohli, P.; Grefenstette, E. “Learning Explanatory Rules from Noisy Data,” ICLR, 2018.
Dong, Y.; Yang, J.; Poon, H. “Language to Logical Form with Neural Attention,” ACL, 2015.
Manhaeve, R.; Demeester, T.; Van den Broeck, G.; Davis, J.; De Raedt, L. “Neural-Symbolic ICML,” ICML, 2020.
Garnelo, M.; et al. “Towards Deep Symbolic Reinforcement Learning,” arXiv, 2016.
Evans, R.; Grefenstette, E. “Learning Explanatory Rules from Noisy Data,” ICLR, 2018.
Xu, Z. et al. “Neural Logic Programming: Learning Rule Inference,” AAAI, 2019.
Sarker, M.; Noor, M.; Semenov, A.; Hossain, L. “Explainable AI via Logical Abstractions,” ECAI, 2022.
Hu, Z.; Ma, X.; Liu, Z.; Hovy, E.; Xing, E. P. “Harnessing Deep Neural Networks with Logic Rules,” ACL, 2016.
Garcez, A. d’Avila; Zaverucha, G.; Besold, T. R. “Logical Neural Networks: A Survey,” ACM Computing Surveys, 2021.
Rocktäschel, T.; Riedel, S. “Learning Knowledge Base Inference with Differentiable Theorem Proving,” ICLR, 2019.
Demski, A.; Farid, Z. “Neural-Symbolic Integration in Knowledge Graph Reasoning,” WWW, 2021.
Li, X.; Li, P.; Ma, J. “Logic-Enhanced Neural Networks for Explainable Classification,” IJCAI, 2020.
Yi, K.; Park, S.; Yoo, J.; Moon, S. “NeuroLog: End-to-End Neural-Symbolic Framework,” NeurIPS, 2022.
Toso, A.; Micheli, A.; d’Avila Garcez, A. “DeepProbLog for Uncertain Reasoning,” NeurIPS, 2019.
Yang, F.; Mao, Y.; Huang, Y.; Xu, Z.; Deng, L. “Neural-Symbolic Reasoner for Question Answering,” ACL, 2021.
Tran, B.; Johnson, M. “Semantic Parsing via Neural-Symbolic Models,” EMNLP, 2018.
Zhang, C.; et al. “Logic-Augmented Neural Networks for Medical Diagnosis,” AAAI, 2022.
Garnelo, M.; et al. “Neural-Symbolic Concept Learner,” NeurIPS, 2019.
Mao, Z.; Zhang, Y.; Huang, R.; He, X. “Neural-Symbolic QA over Knowledge Bases,” ACL, 2020.
Yang, F.; et al. “Interpretable Neural-Symbolic Models with ILP,” ICML, 2022.
Cai, T.; et al. “Multimodal Neural Logic Machines,” CVPR, 2021.
Xu, Z.; et al. “Graph Neural Theorem Provers,” NeurIPS, 2020.
Choi, E.; et al. “Robust Symbolic Reasoning with Neural Modules,” ICLR, 2022.
Sarker, M.; et al. “Rule-guided Neural Networks for Explainability,” IJCAI, 2021.
De Raedt, L.; ND: “Probabilistic Logic Learning with Neural Support,” TPAMI, 2020.
Garnelo, M.; Ros, M.; Shanahan, M. “Few Shot Neural Symbolic Concept Learner,” NeurIPS, 2020.
Rocktäschel, T.; et al. “Differentiable FOL via Tensor Logics,” ICLR, 2021.
Selsam, D.; Liang, P. “Learning a SAT Solver from Single-bit Supervision,” ICLR, 2019.
Yang, Y.; Bennett, J. “Neural-Symbolic Agents in Reinforcement Learning,” AAAI, 2023.
Li, P.; Li, X.; Ma, J. “Neural Logic Inference for Explainable AI,” ECAI, 2020.
Yu, T.; Yang, F.; Fei, G.; Deng, L. “Neural-Symbolic Joint Reasoning for QA,” EMNLP, 2021.
Aditya Gupta, Prassanna Rao Rajgopal . Cybersecurity Platformization: Transforming Enterprise Security in an AI-Driven, Threat-Evolving Digital Landscape. International Journal of Computer Applications. 186, 80 ( Apr 2025), 19-28. DOI=10.5120/ijca2025924719
Zhang, W.; et al. “Symbolic Logic Enhanced BERT for Explainability,” ACL, 2022.
Cai, T.; Wang, Y.; Chen, Z. “Neuro-Symbolic Rule Learning for KBQA,” ICLR, 2020.
Sharma, A.; et al. “Hybrid Logic-Neural Visual Reasoning,” CVPR, 2021.
Cohen, T.; Fine, K. “Differentiable ILP,” NeurIPS, 2022.
Tak, H.; Nam, H. “Symbolic Knowledge Graphs with Neural Embeddings,” ECML PKDD, 2021.
Zhang, F.; et al. “Neural-Symbolic Reinforcement Learning via Logical Constraints,” AAAI, 2022.
Yu, R.; et al. “Combining Induction and Neural Models for Deduction,” ACL, 2023.
Chen, X.; et al. “Logic-guided Multi Task Learning for Explainable AI,” ICML, 2022.
Yang, L.; et al. “Hybrid Neural-Symbolic Image Reasoning,” CVPR, 2022.
Richardson, J.; Gal, Y. “Probabilistic First-Order Logic with Neural Networks,” ICLR, 2023.
Wang, H.; et al. “Graph Logic Neural Networks for Explainable KB Inference,” WWW, 2022.
Toso, A.; et al. “ProbLog for Neural Program Induction,” AAAI, 2021.
Namazifar, S.; et al. “Neural Theorem Proving with Embeddings,” ICLR, 2022.
Liu, T.; et al. “Symbolic-Neural Rule Learning for Science QA,” ACL, 2023.
Chen, Y.; et al. “Hybrid Reasoning for Explainable Clinical AI,” MICCAI, 2022.
Rao, S.; Yin, J.; Tang, J. “Instruction based Neural Symbolic Frameworks,” KDD, 2023.
Similar Articles
- Mariam Nasr, A Contemporary Approach to Platform Synergy: Structured Context Sharing, Programmatic Connectivity Layers, and the Advancement of Intelligent Autonomous Systems , International Journal of Advanced Artificial Intelligence Research: Vol. 2 No. 11 (2025): Volume 02 Issue 11
- Dr. Lucas M. Hoffmann, Dr. Aya El-Masry, ALIGNING EXPLAINABLE AI WITH USER NEEDS: A PROPOSAL FOR A PREFERENCE-AWARE EXPLANATION FUNCTION , International Journal of Advanced Artificial Intelligence Research: Vol. 1 No. 01 (2024): Volume 01 Issue 01
- Dr. Michael Lawson, Dr. Victor Almeida, Securing Deep Neural Networks: A Life-Cycle Perspective On Trojan Attacks And Defensive Measures , International Journal of Advanced Artificial Intelligence Research: Vol. 1 No. 01 (2024): Volume 01 Issue 01
- Adrian T. Blackmoor, Digital Lending Transformation Through Real Time Artificial Intelligence Based Credit Analytics , International Journal of Advanced Artificial Intelligence Research: Vol. 2 No. 11 (2025): Volume 02 Issue 11
- Dr. Amir Reza Khosravi, Dr. Sara Mohammadi, Advanced Cognitive State Analysis of Insomnia Using Computational Architecture for Modeling Thought and Awareness Disruption , International Journal of Advanced Artificial Intelligence Research: Vol. 3 No. 05 (2026): Volume 03 Issue 05
- Olabayoji Oluwatofunmi Oladepo., Opeyemi Eebru Alao, EXPLAINABLE MACHINE LEARNING FOR FINANCIAL ANALYSIS , International Journal of Advanced Artificial Intelligence Research: Vol. 2 No. 07 (2025): Volume 02 Issue 07
- Bagus Candra, Minh Thu Nguyen, A Comprehensive Evaluation Of Shekar: An Open-Source Python Framework For State-Of-The-Art Persian Natural Language Processing And Computational Linguistics , International Journal of Advanced Artificial Intelligence Research: Vol. 2 No. 10 (2025): Volume 02 Issue 10
- Dr. Lukas Reinhardt, Next-Generation Security Operations Centers: A Holistic Framework Integrating Artificial Intelligence, Federated Learning, and Sustainable Green Infrastructure for Proactive Threat Mitigation , International Journal of Advanced Artificial Intelligence Research: Vol. 2 No. 09 (2025): Volume 02 Issue 09
- Dr. Aris Thorne, Generating Dual-Identity Face Impersonations with Generative Adversarial Networks: An Adversarial Attack Methodology , International Journal of Advanced Artificial Intelligence Research: Vol. 2 No. 10 (2025): Volume 02 Issue 10
- Mason Johnson, Forging Rich Multimodal Representations: A Survey of Contrastive Self-Supervised Learning , International Journal of Advanced Artificial Intelligence Research: Vol. 2 No. 11 (2025): Volume 02 Issue 11
You may also start an advanced similarity search for this article.