New principles of finding and removing elements of mathematical model for reducing computational and time complexity

被引：2

作者：

Matviychuk, Yaroslav ^{[1
]}

Kryvinska, Natalia ^{[2
]}

Shakhovska, Nataliya ^{[1
]}

Poniszewska-Maranda, Aneta ^{[3
]}

机构：

[1] Lviv Polytech Natl Univ, Lvov, Lviv Oblast, Ukraine

[2] Comenius Univ, Bratislava, Slovakia

[3] Lodz Univ Technol, Lodz, Poland

来源：

INTERNATIONAL JOURNAL OF GRID AND UTILITY COMPUTING | 2023年 / 14卷 / 04期

关键词：

regularisation; reduction; identification procedure; incorrectness; neural network; NEURAL-NETWORKS;

D O I：

10.1504/IJGUC.2023.132625

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The original principle of removing elements of a mathematical model based on its parametric identification of neural network is proposed in the paper. The essence of proposed method is to find a functional subset with less variable results and higher accuracy than for the initial functional set of the model. It allows reducing the computational and time complexity of the applications built on the model. The comparison with dropout technique shows the 1, 1 decreasing of root mean squared error. In addition, reducing the complexity allows increasing the accuracy of neural network models. Therefore, reducing the number of parameters is an essential step in data preprocessing used in almost all modern systems. However, known methods of reducing the dimension depend on the problem area, making it impossible to use them in ensemble models.

引用

页码：400 / 410

页数：12

共 50 条

[41] Mitigating interference and reducing detection complexity in asynchronous cooperative relay network utilising new distributed space time block coding
Elazreg, Abdulghani M.
Kharaz, Ahmad H.
IET COMMUNICATIONS, 2021, 15 (01) : 14 - 21
[42] A new ZNN model for finding discrete time-variant matrix square root: From model design to parameter analysis
Jiang, Chao
Zhang, Yixiang
Mou, Chao
Li, Bin
Sun, Xiaobing
Shi, Yang
JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2023, 431
[43] A new distributed time series evolution prediction model for dam deformation based on constituent elements
Li, Mingchao
Shen, Yang
Ren, Qiubing
Li, Heng
ADVANCED ENGINEERING INFORMATICS, 2019, 39 : 41 - 52
[44] Aircraft anti-ice system: Evaluation of system performance with a new time dependent mathematical model
Zilio, Claudio
Patricelli, Luca
APPLIED THERMAL ENGINEERING, 2014, 63 (01) : 40 - 51
[45] New Approach to Nonlinear Dynamic Analysis of Reinforced Concrete 3D Frames; An Accurate and Computational Efficient Mathematical Model
Munteanu, Ruben Iacob
Mota, Florin
Calofir, Vasile
Baciu, Catalin
APPLIED SCIENCES-BASEL, 2022, 12 (03):
[46] Development of ANFIS model for air quality forecasting and input optimization for reducing the computational cost and time (vol 128, pg 246, 2016)
Prasad, Kanchan
Gorai, Amit Kumar
Goyal, Pramila
ATMOSPHERIC ENVIRONMENT, 2016, 142 : 370 - 370
[47] Developing a New Multi-Objective Mathematical Model for Electric Vehicles Routing with Charging Stations and Time Windows
Chen, Tzu-Chia
Li, Yong
INDUSTRIAL ENGINEERING AND MANAGEMENT SYSTEMS, 2021, 20 (02): : 279 - 288
[48] ON A NEW, ONE-DIMENSIONAL, TIME-DEPENDENT MODEL FOR TURBULENCE AND CONVECTION .1. A BASIC DISCUSSION OF THE MATHEMATICAL-MODEL
GEHMEYR, M
WINKLER, KHA
ASTRONOMY & ASTROPHYSICS, 1992, 253 (01) : 92 - 100
[49] Hierarchical event streams and event dependency graphs: A new computational model for embedded real-time systems
Albers, Karsten
Bodmann, Frank
Slomka, Frank
18TH EUROMICRO CONFERENCE ON REAL-TIME SYSTEMS, PROCEEDINGS, 2006, : 97 - +
[50] New mathematical model for determining time-dependent adsorption and diffusion of dyes into fibers through dye sorption curves in combination shades .1. Mathematical fundamentals
Cleve, E
Bach, E
Denter, U
Duffner, H
Schollmeyer, E
TEXTILE RESEARCH JOURNAL, 1997, 67 (10) : 701 - 706

← 1 2 3 4 5 →