Regularization of Machine Learning and Linear Algebra

Regularization of Machine Learning and Linear Algebra Full article

Conference

8th International Conference on Computer Science and Artificial Intelligence
06-08 Dec 2024 , Beijing

Source

Proceedings of the 2024 8th International Conference on Computer Science and Artificial Intelligence
Compilation, ACM. 2025. ISBN 979-8-4007-1818-2.

Output data

Year: 2024, Pages: 327-332 Pages count : 6 DOI: 10.1145/3709026.3709071

Tags

linear neural network, machine learning, system of linear algebraic equations

Authors

Liu Shuang ¹ , Kabanikhin Sergey Igorevich ² , Strijhak Sergei Vladimirovich ³

Affiliations

1	Novosibirsk State University, Novosibirsk, Akademgorodok, Russian Federation
2	Sobolev Institute of Mathematics Siberian Branch of the Russian Academy of Sciences, Novosibirsk, Russian Federation
3	Ivannikov Institute of System Programming of the Russian Academy of Sciences, Moscow, Russian Federation

This paper explores the connection between systems of linear algebraic equations (SLAE) and machine learning methods, including regularization techniques, to establish a more novel neural network model based on linear neural networks. The goal is to construct a weight matrix for the neural network, which, by simulating the process of finding pseudo-solutions to SLAE, can generate the optimal answer for any input data. In this new neural network model, linear operations are performed first, followed by nonlinear operations, ultimately yielding an optimized weight matrix that serves as the pseudo-solution to the SLAE. The paper demonstrates how linear neural networks can be simplified to SLAE, how adding nonlinear layers to the linear neural network model can improve accuracy, and how machine learning methods can be used to find pseudo-solutions to SLAE.

Liu S. , Kabanikhin S.I. , Strijhak S.V.
Regularization of Machine Learning and Linear Algebra
In compilation Proceedings of the 2024 8th International Conference on Computer Science and Artificial Intelligence. – ACM., 2024. – C.327-332. – ISBN 979-8-4007-1818-2. DOI: 10.1145/3709026.3709071 Scopus OpenAlex

Published print:	Feb 15, 2025
Published online:	Feb 15, 2025

Scopus:	2-s2.0-85219594269
OpenAlex:	W4407601566

Пока нет цитирований