|
Intelligent systems. Theory and applications, 2022, Volume 26, Issue 2, Pages 42–60
(Mi ista406)
|
|
|
|
This article is cited in 2 scientific papers (total in 2 papers)
Part 2. Special Issues in Intellectual Systems Theory
On the construction of an explicit neural network architecture that approximates particle-linear functions
V. G. Shishlyakov Lomonosov Moscow State University, Faculty of Mechanics and Mathematics
Abstract:
This work considers the question of discovering an upper-bound estimation of parameters quantity of neural network architecture well-approximating particle-linear dependances. The main result of this article consists of the theorem asserting that any particle-linear function can be approximated with any degree of precision on the big part of space by neural network with sigmoidal activation functions. This theorem has a constructive proof, i.e. neural network architecture with mentioned features building explicitly.
Keywords:
schemes of functional elements, neural networks, architecture, approximation, upper-bound estimation, particle-linear functions.
Citation:
V. G. Shishlyakov, “On the construction of an explicit neural network architecture that approximates particle-linear functions”, Intelligent systems. Theory and applications, 26:2 (2022), 42–60
Linking options:
https://www.mathnet.ru/eng/ista406 https://www.mathnet.ru/eng/ista/v26/i2/p42
|
Statistics & downloads: |
Abstract page: | 33 | Full-text PDF : | 27 | References: | 10 |
|