TARU PUBLICATIONS
Journal of Interdisciplinary Mathematics cover
Hybrid ·Peer-reviewed·ISSN (Online): 2169-012X·ISSN (Print): 0972-0502

Monthly Journal: Publishes the methodological and theoretical role of mathematics and mathematical applications underpinning scientific research.

Issues up to 2022 co-published with and available at:Taylor & Francis Online
submissions@tarupublications.com
Open Access Research Article

Mathematical models for cognitive systems using differential geometry and reinforcement learning

, , , * , ,

* Corresponding author · click or hover a name for details

pp. 2089–2097Vol. 28Issue 6September 2025DOI: 10.47974/JIM-2350XML
Received:
10 Dec 2024
Published Online:
30 Sep 2025
Article type:
Research Article
Language:
EN
Article no.:
JIM-2350
Pages:
2089–2097

Abstract

This work presents a novel creative approach to describe cognitive systems by combining differential geometry with reinforcement learning. We propose a mathematical approach primarily based on geometric properties of facts manifolds to improve cognitive models studying functionality. Differential geometry facilitates us to set up cognitive activities over curved surfaces. This allows us to depict the intellectual mechanisms concerned in learning and decision-making extra exactly. Considering they apply reinforcement mastering, those models might also adapt and enhance their behaviour relying on remarks from their surroundings. This hybrid model plays better in tests of challenging cognitive responsibilities such spatial navigation and sample reputation by using the use of the intrinsic geometric shape of the statistics. We carefully observe the convergence traits of the proposed models. The findings reveal that the geometric method not simplest clarifies cognitive techniques but additionally hastens mastering and guarantees elevated dependability of the models. Our results reveal that artificial cognitive systems with higher intelligence and efficiency might be produced from these mathematical models. This might have a significant impact on disciplines such robotics, self-driving automobiles, and the creation of intelligent systems.

Keywords

Subject Classifications

68Q87

References

[1] R. Friedman, “Geometry-Based Deep Learning in the Natural Sciences,” Encyclopedia, vol. 3, pp. 781–794 (2023).
[2] L. Chen, K. Lu, A. Rajeswaran, K. Lee, A. Grover, M. Laskin, P. Abbeel, A. Srinivas, and I. Mordatch, “Decision Transformer: Reinforcement Learning via Sequence Modeling,” in Advances in Neural Information Processing Systems, vol. 34, pp. 15084–15097 (2021).
[3] R. Friedman, “A Hierarchy of Interactions between Pathogenic Virus and Vertebrate Host,” Symmetry, vol. 14, pp. 2274 (2022).
[4] F. Wong, A. Krishnan, E. J. Zheng, H. Stark, A. L. Manson, A. M. Earl, T. Jaakkola, and J. J. Collins, “Benchmarking AlphaFold-enabled molecular docking predictions for antibiotic discovery,” Molecular Systems Biology, vol. 18, pp. e11081 (2022).
[5] A. Montemurro, V. Schuster, H. R. Povlsen, A. K. Bentzen, V. Jurtz, W. D. Chronister, A. Crinklaw, S. R. Hadrup, O. Winther, B. Peters, et al., “NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCRα and β sequence data,” Communications Biology, vol. 4, pp. 1060 (2021).
[6] P. Bradley, “Structure-based prediction of T cell receptor: Peptide-MHC interactions,” eLife, vol. 12, pp. e82813 (2023).
[7] A. C. Ehresmann, M. Béjean, and J.-P. Vanbremeersch, “A Mathematical Framework for Enriching Human–Machine Interactions,” Machine Learning and Knowledge Extraction, vol. 5, pp. 597–610 (2023).
[8] K. Sivamayil, E. Rajasekar, B. Aljafari, S. Nikolovski, S. Vairavasundaram, and I. Vairavasundaram, “A Systematic Study on Reinforcement Learning Based Applications,” Energies, vol. 16, pp. 1512 (2023).
[9] S. Sahil, A. Zaidi, M. Samar, A. Aslam, N. Kanwal, M. Asghar, and B. Lee, “A Survey of Modern Deep Learning Based Object Detection Models,” Digital Signal Processing, vol. 126, pp. 103514 (2022).
[10] P. Sahane, M. Gulhane, N. Rakesh, S. M. Mahalakshmi Naidu, M. Grover, and V. Mahajan, “Evaluating lightweight encryption schemes for resource-constrained devices in wireless sensor networks,” J. Discrete Math. Sci. Cryptogr., vol. 28, no. 5-A, pp. 1803–1812 (2025).
[11] M. Gulhane and T. Sajana, “Integrating optimized ensemble learning and explainable AI for accurate heart disease diagnosis,” J. Inf. Optim. Sci., vol. 45, no. 8, pp. 2369–2378 (2024).

Views: 225Downloads: 95Citations: 1