Modeling and sensitivity analysis of neural networks

被引：10

作者：

Lamy, D ^{[1
]}

机构：

[1] ECOLE CENT LILLE,CNRS D1440,URA,LAB AUTOMAT & INFORMAT IND LILLE,F-59651 VILLENEUVE DASCQ,FRANCE

来源：

MATHEMATICS AND COMPUTERS IN SIMULATION | 1996年 / 40卷 / 5-6期

关键词：

D O I：

10.1016/0378-4754(95)00005-4

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

This paper investigates the use of neural networks for the identification of linear time invariant dynamical systems. Two classes of networks, namely the multilayer feedforward network and the recurrent network with linear neurons, are studied. A notation based on Kronecker product and vector-valued function of matrix is introduced for neural models. It permits to write a feedforward network as a one step ahead predictor used in parameter estimation. A special attention is devoted to system theory interpretation of neural models. Sensitivity analysis can be formulated using derivatives based on the above-mentioned notation.

引用

页码：535 / 548

页数：14

共 50 条

[31] Sensitivity and generalized analytical sensitivity expressions for quantitative analysis using convolutional neural networks
Shariat, Kourosh
Kirsanov, Dmitry
Olivieri, Alejandro C.
Parastar, Hadi
ANALYTICA CHIMICA ACTA, 2022, 1192
[32] Modeling effect in pharmacoeconomics analysis using artificial neural networks
Polak, S
Skowron, A
Brandys, J
Mendyk, A
VALUE IN HEALTH, 2004, 7 (06) : 683 - 684
[33] Sensitivity in PET: Neural networks as an alternative to Compton photons LOR analysis
Michaud, Jean-Baptiste
Brunet, Charles-Antoine
Rafecas, Magdalena
Lecomte, Roger
Fontaine, Rejean
Rechka, Sanae
2007 IEEE NUCLEAR SCIENCE SYMPOSIUM CONFERENCE RECORD, VOLS 1-11, 2007, : 3594 - +
[34] Modeling and analysis of artificial neural networks applied in operations research
da Silva, IN
de Souza, AN
Bordon, ME
MANUFACTURING, MODELING, MANAGEMENT AND CONTROL, PROCEEDINGS, 2001, : 315 - 320
[35] Numerical sensitivity analysis of HTPB counterflow combustion using neural networks
Bojko, Brian T.
Geipel, Clayton M.
Fisher, Brian T.
Kessler, David A.
Combustion and Flame, 2025, 271
[36] Analysis of Recurrent Neural Networks for Probabilistic Modeling of Driver Behavior
Morton, Jeremy
Wheeler, Tim A.
Kochenderfer, Mykel J.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2017, 18 (05) : 1289 - 1298
[37] Sensitivity analysis by neural networks applied to power systems transient stability
Lotufo, Anna Diva P.
Lopes, Mara Lucia M.
Minussi, Carlos R.
ELECTRIC POWER SYSTEMS RESEARCH, 2007, 77 (07) : 730 - 738
[38] Modeling and analysis of the electrical properties of PZT through neural networks
Guo, D
Li, LT
Nan, CW
Xia, JT
Gui, ZL
JOURNAL OF THE EUROPEAN CERAMIC SOCIETY, 2003, 23 (12) : 2177 - 2181
[39] Variance decomposition-based sensitivity analysis via neural networks
Marseguerra, M
Masini, R
Zio, E
Cojazzi, G
RELIABILITY ENGINEERING & SYSTEM SAFETY, 2003, 79 (02) : 229 - 238
[40] Analyzing the Sensitivity of Deep Neural Networks for Sentiment Analysis: A Scoring Approach
Alhazmi, Ahoud
Zhang, Wei Emma
Sheng, Quan Z.
Aljubairy, Abdulwahab
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,

← 1 2 3 4 5 →