SELECTIVE TRAINING OF FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING MATRIX PERTURBATION-THEORY

被引：9

作者：

HUNT, SD ^{[1
]}

DELLER, JR ^{[1
]}

机构：

[1] MICHIGAN STATE UNIV,DEPT ELECT ENGN,E LANSING,MI 48824

来源：

NEURAL NETWORKS | 1995年 / 8卷 / 06期

基金：

美国国家科学基金会;

关键词：

SELECTIVE TRAINING; EFFICIENT TRAINING; FEEDFORWARD NETWORKS; ARTIFICIAL NEURAL NETWORKS; PERTURBATION THEORY; NONLINEAR OPTIMIZATION; SUPERVISED LEARNING; NEW TRAINING ALGORITHM; PATTERN RECOGNITION;

D O I：

10.1016/0893-6080(95)00030-4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Many training algorithms for feedforward neural networks suffer from slow convergence. A new training method is presented which exploits results from matrix perturbation theory for significant training time improvement. This theory is used to assess the effect of a particular training pattern on the weight estimates prior to its inclusion in any iteration. Data which do not significantly change the weights are nor used in that iteration obviating the computational expense of updating.

引用

页码：931 / 944

页数：14

共 50 条

[31] Testing Feedforward Neural Networks Training Programs
Ben Braiek, Houssem
Khomh, Foutse
ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY, 2023, 32 (04)
[32] MINIMIZATION METHODS FOR TRAINING FEEDFORWARD NEURAL NETWORKS
VANDERSMAGT, PP
NEURAL NETWORKS, 1994, 7 (01) : 1 - 11
[33] On fault tolerant training of feedforward neural networks
Arad, BS
ElAmawy, A
NEURAL NETWORKS, 1997, 10 (03) : 539 - 553
[34] Leakage detection in water distribution networks using hybrid feedforward artificial neural networks
Fallahi, Hamideh
Jalili Ghazizadeh, Mohammadreza
Aminnejad, Babak
Yazdi, Jafar
AQUA-WATER INFRASTRUCTURE ECOSYSTEMS AND SOCIETY, 2021, 70 (05) : 637 - 653
[35] Training feedforward neural networks using orthogonal iteration of the Hessian eigenvectors
Hunter, A
IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL II, 2000, : 173 - 178
[36] NEW ALGORITHMS FOR TRAINING FEEDFORWARD NEURAL NETWORKS
KAK, S
PATTERN RECOGNITION LETTERS, 1994, 15 (03) : 295 - 298
[37] Regularization and feedforward artificial neural network training with noise
Chandra, P
Singh, Y
PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 2366 - +
[38] Neural Smithing – Supervised Learning in Feedforward Artificial Neural Networks
Barbara Hammer
Pattern Analysis & Applications, 2001, 4 (1): : 73 - 74
[39] GENERALIZED RAYLEIGH-SCHRODINGER PERTURBATION-THEORY IN MATRIX FORM
BESALU, E
CARBO, R
JOURNAL OF MATHEMATICAL CHEMISTRY, 1994, 15 (3-4) : 397 - 406
[40] S-MATRIX UNITARIZATION WITHIN REACTIVE PERTURBATION-THEORY
HORN, TR
ENO, L
JOURNAL OF CHEMICAL PHYSICS, 1986, 85 (10): : 5711 - 5716

← 1 2 3 4 5 →