Regularization of linear machine learning problems
Abstract
In this paper, we consider the simplest version of a linear neural network (LNN). Assuming that for training (constructing an optimal weight matrix ) we have a set of training pairs, i.e. we know the input data \begin{equation} G=\left\{g^{\left(1\right)},g^{\left(2\right)},\cdots,g^{\left(K\right)}\right\}, \end{equation} as well as the correct answers to these input data \begin{equation} H=\left\{h^{\left(1\right)},h^{\left(2\right)},\cdots,h^{\left(K\right)}\right\}. \end{equation} We will study the possibilities of constructing a weight matrix of a neural network that will give correct answers to arbitrary input data based on the connection of the specified problem with a system of linear algebraic equations (SLAE). Consider a class of neural networks in which each neuron has only one output signal and performs linear operations. We will show how such LNEs are reduced to SLAEs. Since the questions and the correct answers are known to us, the desired weight matrix must satisfy the equations \begin{equation} Qg^{\left(k\right)}=h^{\left(k\right)}, k=1,2,\cdots,K. \end{equation} It is required to restore . In the general case, the matrix is rectangular , is the row number, and , . Let be a matrix composed of columns , and be a matrix composed of columns . Then, with respect to , we obtain a matrix SLAE. \begin{equation} Q_{MN}G_{NK}=H_{MK}. \end{equation} This paper will present methods for regularizing the constructed system.
Keywords
Cite
@article{arxiv.2408.04871,
title = {Regularization of linear machine learning problems},
author = {S. Liu and S. I. Kabanikhin and S. V. Strijhak},
journal= {arXiv preprint arXiv:2408.04871},
year = {2024}
}
Comments
in Russian language