Exploring elliptic geometry in neural networks : The concept of elliptic neural networks (ENN)

Verma, Vivek Kumar; Saini, Bhavna; Yadav, Anju; Dadheech, Pankaj

doi:10.47974/JDMSC-1906

Open Access Research Article

Exploring elliptic geometry in neural networks : The concept of elliptic neural networks (ENN)

Vivek Kumar Vermavermavivek123@gmail.comDepartment of Information TechnologyManipal University JaipurJaipur, Rajasthan, IndiaView full profile → , Bhavna Sainibhavnasaini10@gmail.comDepartment of Data Science AnalyticsCentral University RajasthanIndiaView full profile → , ^*Anju YadavCorresponding authoranju.anju.yadav@gmail.comDepartment of Information TechnologyManipal University JaipurJaipur, Rajasthan, IndiaView full profile → , Pankaj Dadheechpankajdadheech777@gmail.comDepartment of Computer Science & EngineeringManagement & GramothanSwami Keshvanand Institute of TechnologyJaipur, Rajasthan, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 501–512Vol. 27Issue 2-AMarch 2024DOI: 10.47974/JDMSC-1906 Crossmark XML

Published Online:: 06 Apr 2024
Article type:: Research Article
Language:: EN
Article no.:: JDMSC-1906
Pages:: 501–512

Abstract

The exploration of non-Euclidean geometries in the context of neural network architectures presents a novel avenue for enhancing the processing of complex data structures. This paper introduces the concept of Elliptic Neural Networks (ENN), a framework that integrates the intrinsic properties of elliptic geometry into the fabric of neural computation. Characterized by constant positive curvature and closed geodesic paths, elliptic geometry provides a unique perspective for representing data, especially advantageous for configurations exhibiting cyclic and dense hierarchical interconnections. We begin by delineating the fundamental aspects of elliptic geometry, focusing on its impact on conventional notions of distance and global structural interpretation within data sets. This foundational understanding paves the way for our proposed mathematical schema for ENNs. Within this framework, we articulate the methodologies for embedding data in elliptic spaces and adapt neural network operations by encompassing neuron activation, signal propagation, and learning paradigms to conform to the topological idiosyncrasies of elliptic geometry. In this paper addressing the implementation of ENNs, we discuss the computational challenges and the development of novel algorithms requisite for navigating the elliptic geometric landscape. The prospective applications of ENNs are extensive and diverse, ranging from the enhancement of cyclic pattern recognition in time-series analysis to more sophisticated representations in graph-based data and natural language processing tasks. This theoretical exposition aims to set the groundwork for subsequent empirical research to validate the proposed model and assess its practical performance relative to conventional neural network architectures. By harnessing the distinctive characteristics of elliptic geometry, ENNs mark a significant stride towards enriching the arsenal of machine learning methodologies, potentially leading to more versatile and efficacious computational tools in data analysis and artificial intelligence.

Keywords

Elliptic neural networks (ENN)Non-euclidean geometry in machine learning Elliptic geometry in AI Neural networks and elliptic space Machine learning and elliptic geometry

Subject Classifications

68T05

References

[1] R. I. Balam, F. Hernandez-Lopez, J. Trejo-Sanchez, and M. U. Zapata, ‘An immersed boundary neural network for solving elliptic equations with singular forces on arbitrary domains’. Mathematical Biosciences and Engineering, 18(1), pp. 1-22,(2021).
[2] S. H. Chowdhury, Md. R. Sany, Md. H. Ahamed, S. K. Das, F. R. Badal, P. Das, Z. Tasneem, Md. M. Hasan, Md. R. Islam, Md. F. Ali, S. H. Abhi, Md. M. Islam, and S. K. Sarker, ‘A State-of-the-Art Computer Vision Adopting Non-Euclidean Deep-Learning Models’, International Journal of Intelligent Systems, vol. 8674641, pp 1-33, (2023).
[3] G. M. Jay, ‘Euclidean and Non-Euclidean Geometries’, New York: W.H. Freeman and Company, (2008).
[4] G., Han, L. Sun, and J. X. Wang, ‘PhyGeoNet: Physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain’, Journal of Computational Physics, 428, 110079 (2021).
[5] M. A. Nabian, and H. Meidani, ‘A deep learning solution approach for high-dimensional random differential equation’s, Probabilistic Engineering Mechanics, 57, pp. 14–25, (2019).
[6] S. Karumuri, R. Tripathy, I. Bilionis, and J. Panchal, ‘Simulator-free solution of high dimensional stochastic elliptic partial differential equations using deep neural networks’, Journal of Computational Physics, 404, pp. 109120, (2020).
[7] K. Stefan, A. Steinicke, and M. Szölgyenyi, ‘A deep neural network algorithm for semilinear elliptic PDEs with applications in insurance mathematics’, Risks, 8(4), (2020).
[8] Anil Kumar & Sandeep Kumar Sharma. Information cryptography using cellular automata and digital image processing, Journal of Discrete Mathematical Sciences and Cryptography, 25:4, 1105-1111 (2022), DOI: 10.1080/09720529.2022.2072437.
[9] D. Thameur, W. Ouarda, H. Boubaker, and A. M. Alimi, ‘Deep neural network for online writer identification using beta-elliptic model’, International joint conference on neural networks (IJCNN), pp. 1863-1870. IEEE, (2016).
[10] H. Esam AA, S. Aldosary, H. Khaled, and T. M. Hassan. ‘Authenticated Public Key Elliptic Curve Based on Deep Convolutional Neural Network for Cybersecurity Image Encryption Application’, Sensors 23, 14, (2023).
[11] K. Matija, and D. Vlah. ‘Ranks of elliptic curves and deep neural networks’, Research in Number Theory 9, 3, 53, (2023).
[12] Sharma, Sandeep Kumar, Kumar, Anil, Ashtagi, Rashmi & Jain, Rekha. OCA: An intelligent model for improving security breach of biometric based authentication systems, Journal of Discrete Mathematical Sciences and Cryptography, 26:5, 1415–1425 (2023), DOI: 10.47974/JDMSC-1765.
[13] D. Wenbo, P. Roy, C. Peng, and V. Isler, ‘Ellipse R-CNN: Learning to infer elliptical object from clustering and occlusion’, IEEE Transactions on Image Processing ,30, pp. 2193-2206 (2021).
[14] C. Yunpeng, S. AL de Ridder, S. Rost, Z. Guo, X. Wu, S. Li, and Y. Chen, ‘Physics-Informed Neural Networks for Elliptical-Anisotropy Eikonal Tomography: Application to Data From the Northeastern Tibetan Plateau’, Journal of Geophysical Research: Solid Earth, 128, no. 12, (2023).
[15] P. Hung-Wen, S. Lee, and C. Lee, ‘An oblique elliptical basis function network approach for supervised learning applications’, Applied Soft Computing, 60, pp. 552-563, (2017).

Views: 220Downloads: 56Citations: 0