Evaluation of the feedforward neural network covariance matrix error

被引：0

作者：

Abid, S ^{[1
]}

Fnaiech, F ^{[1
]}

Najim, M ^{[1
]}

机构：

[1] ESSTT, Tunis 1008, Tunisia

来源：

2000 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS, VOLS I-VI | 2000年

关键词：

Neural Network (NN); covariance matrix error; perturbation model;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

This paper presents a theoretical approach for the evaluation of a feedforward neural network output error matrix. It is shown how the input errors and the different weights errors are linked determine an error bound. The formulas of the output covariance matrix error is derived arising the sensitivity the additive weight perturbations or input perturbations, This analytical formulas is validated via simulation of a function approximation example showing that the errors and the different weights errors are linked and spread over the neural network to form the output covariance matrix error which could may be used determine an error bound. The formulas of the output function approximation example showing that the theoretical result is in agreement with simulation result.

引用

页码：3482 / 3485

页数：4

共 50 条

[11] A feedforward unitary equivariant neural network
Ma, Pui-Wai
Chan, T. -H. Hubert
[J]. NEURAL NETWORKS, 2023, 161 : 154 - 164
[12] On the Space of Coefficients of a Feedforward Neural Network
Valluri, Dinesh
Campbell, Rory
[J]. 2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
[13] On the Effectiveness of Interpretable Feedforward Neural Network
Li, Miles Q.
Fung, Benjamin C. M.
Abusitta, Adel
[J]. 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
[14] Stable criticality in a feedforward neural network
Ceccatto, A
Navone, H
Waelbroeck, H
[J]. REVISTA MEXICANA DE FISICA, 1996, 42 (05) : 810 - 825
[15] Transmission of neural activity in a feedforward network
Wang, ST
Wang, W
[J]. NEUROREPORT, 2005, 16 (08) : 807 - 811
[16] Training of a feedforward multiple-valued neural network by error backpropagation with a multilevel threshold function
Asari, VK
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (06): : 1519 - 1521
[17] Generalized feedforward neural network classifier
Arulampalam, G
Bouzerdoum, A
[J]. PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 1429 - 1434
[18] A multilayer feedforward fuzzy neural network
Savran, Aydogan
[J]. ARTIFICIAL INTELLIGENCE AND NEURAL NETWORKS, 2006, 3949 : 78 - 83
[19] Genetic design for feedforward neural network
Lu, Jianfeng
Shang, Shang
Yang, Jingyu
[J]. Nanjing Li Gong Daxue Xuebao/Journal of Nanjing University of Science and Technology, 1999, 23 (06): : 486 - 489
[20] Local coupled feedforward neural network
Sun, Jianye
[J]. NEURAL NETWORKS, 2010, 23 (01) : 108 - 113

← 1 2 3 4 5 →