Abstract
In this paper, we use the representation morphism concept to analyze the connection between two recurrent neural networks, primarily when we evaluate the neural network function between two isomorphic neural networks. We construct the set of all isomorphic classes of recurrent neural networks. We build the set by the action of the isomorphism group on the set of all recurrent neural networks that have invertible weight. By the group’s action, we get the set of orbits and call it the moduli space. We analyze the moduli space to get its dimensions.
Full text article
References
Q. Zhang and Y. Wang, “Construction of composite mode of sports education professional football teaching based on sports video recognition technology,” in 2020 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE), pp. 1889–1893, 2020. https://doi.ieeecomputersociety.org/10.1109/ICMCCE51767.2020.00414.
F. Sch¨oller, M. Blanke, M. Plenge-Feidenhans’, and L. Nalpantidis, “Vision-based object tracking in marine environments using features from neural network detections,” IFAC-PapersOnLine (21st IFAC World Congress), vol. 53, no. 2, pp. 14517–14523, 2020. https://doi.org/10.1016/j.ifacol.2020.12.1455.
S. Kumari, S. Aravindakshan, U. Jain, and V. Srinivasa Chakravarthy, “Convolutional elman jordan neural network for reconstruction and classification using attention window,” in Innovations in Computational Intelligence and Computer Vision (M. K. Sharma, V. S. Dhaka, T. Perumal, N. Dey, and J. M. R. S. Tavares, eds.), (Singapore), pp. 173–181, Springer Singapore, 2021. https://doi.org/10.1007/978-981-15-6067-5_20.
M. Armenta, T. Judge, N. Painchaud, Y. Skandarani, C. Lemaire, G. Gibeau Sanchez, P. Spino, and P.-M. Jodoin, “Neural teleportation,” Mathematics, vol. 11, no. 2, 2023. https://www.mdpi.com/2227-7390/11/2/480.
I. Assem, A. Skowronski, and D. Simson, Elements of the Representation Theory of Associative Algebras: Techniques of Representation Theory. London Mathematical Society Student Texts, Cambridge University Press, 2006.
M. Armenta and P.-M. Jodoin, “The representation theory of neural networks,” Mathematics, vol. 9, no. 24, 2021. https://www.mdpi.com/2227-7390/9/24/3216.
L. C. Wanditra, I. M. Alamsyah, and G. Rachmaputri, “Wave packet transform on finite abelian group,” Southeast Asian Bulletin of Mathematics, vol. 44, no. 6, pp. 853–857, 2020.
L. C. Wanditra, I. Muchtadi-Alamsyah, and D. Nasution, “Artificial neural networks using quiver representations of finite cyclic groups,” Symmetry, vol. 15, no. 12, 2023. https://www.mdpi.com/2073-8994/15/12/2110.
I. M. Isaacs, Algebra: a graduate course. Graduate Studies in Mathematics 100, American Mathematical Society, 2009.
S. Shanmugam, R. Vadivel, M. Rhaima, and H. Ghoudi, “Improved results on an extended dissipative analysis of neural networks with additive time-varying delays using auxiliary function-based integral inequalities,” AIMS Mathematics, vol. 8, no. 9, pp. 21221–21245, 2023. https://doi.org/10.3934/math.20231082.
M. Armenta, T. Br¨ustle, S. Hassoun, and M. Reineke, “Double framed moduli spaces of quiver representations,” Linear Algebra and its Applications, vol. 650, pp. 98–131, 2022. https://doi.org/10.1016/j.laa.2022.05.018.
A. Belov-Kanel, L. Rowen, and U. V. and, “Application of full quivers of representations of algebras, to polynomial identities,” Communications in Algebra, vol. 39, no. 12, pp. 4536–4551, 2011. https://doi.org/10.1080/00927872.2011.616432.
Authors
Copyright (c) 2025 Journal of the Indonesian Mathematical Society
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Article Details
